Pub Date : 2022-10-10DOI: 10.48550/arXiv.2210.04477
Chunhui Zhang, Yixiong Chen, Li Liu, Qiong Liu, Xiaoping Zhou
The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning deep neural networks (DNNs), and thus is difficult to learn transferable feature representations. This work proposes a hierarchical contrastive learning (HiCo) method to improve the transferability for the US video model pretraining. HiCo introduces both peer-level semantic alignment and cross-level semantic alignment to facilitate the interaction between different semantic levels, which can effectively accelerate the convergence speed, leading to better generalization and adaptation of the learned model. Additionally, a softened objective function is implemented by smoothing the hard labels, which can alleviate the negative effect caused by local similarities of images between different classes. Experiments with HiCo on five datasets demonstrate its favorable results over state-of-the-art approaches. The source code of this work is publicly available at https://github.com/983632847/HiCo.
{"title":"HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining","authors":"Chunhui Zhang, Yixiong Chen, Li Liu, Qiong Liu, Xiaoping Zhou","doi":"10.48550/arXiv.2210.04477","DOIUrl":"https://doi.org/10.48550/arXiv.2210.04477","url":null,"abstract":"The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning deep neural networks (DNNs), and thus is difficult to learn transferable feature representations. This work proposes a hierarchical contrastive learning (HiCo) method to improve the transferability for the US video model pretraining. HiCo introduces both peer-level semantic alignment and cross-level semantic alignment to facilitate the interaction between different semantic levels, which can effectively accelerate the convergence speed, leading to better generalization and adaptation of the learned model. Additionally, a softened objective function is implemented by smoothing the hard labels, which can alleviate the negative effect caused by local similarities of images between different classes. Experiments with HiCo on five datasets demonstrate its favorable results over state-of-the-art approaches. The source code of this work is publicly available at https://github.com/983632847/HiCo.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81227823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-10DOI: 10.48550/arXiv.2210.04570
L. Bonfiglioli, M. Toschi, Davide Silvestri, Nicola Fioraio, Daniele De Gregorio
We present Eyecandies, a novel synthetic dataset for unsupervised anomaly detection and localization. Photo-realistic images of procedurally generated candies are rendered in a controlled environment under multiple lightning conditions, also providing depth and normal maps in an industrial conveyor scenario. We make available anomaly-free samples for model training and validation, while anomalous instances with precise ground-truth annotations are provided only in the test set. The dataset comprises ten classes of candies, each showing different challenges, such as complex textures, self-occlusions and specularities. Furthermore, we achieve large intra-class variation by randomly drawing key parameters of a procedural rendering pipeline, which enables the creation of an arbitrary number of instances with photo-realistic appearance. Likewise, anomalies are injected into the rendering graph and pixel-wise annotations are automatically generated, overcoming human-biases and possible inconsistencies. We believe this dataset may encourage the exploration of original approaches to solve the anomaly detection task, e.g. by combining color, depth and normal maps, as they are not provided by most of the existing datasets. Indeed, in order to demonstrate how exploiting additional information may actually lead to higher detection performance, we show the results obtained by training a deep convolutional autoencoder to reconstruct different combinations of inputs.
{"title":"The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization","authors":"L. Bonfiglioli, M. Toschi, Davide Silvestri, Nicola Fioraio, Daniele De Gregorio","doi":"10.48550/arXiv.2210.04570","DOIUrl":"https://doi.org/10.48550/arXiv.2210.04570","url":null,"abstract":"We present Eyecandies, a novel synthetic dataset for unsupervised anomaly detection and localization. Photo-realistic images of procedurally generated candies are rendered in a controlled environment under multiple lightning conditions, also providing depth and normal maps in an industrial conveyor scenario. We make available anomaly-free samples for model training and validation, while anomalous instances with precise ground-truth annotations are provided only in the test set. The dataset comprises ten classes of candies, each showing different challenges, such as complex textures, self-occlusions and specularities. Furthermore, we achieve large intra-class variation by randomly drawing key parameters of a procedural rendering pipeline, which enables the creation of an arbitrary number of instances with photo-realistic appearance. Likewise, anomalies are injected into the rendering graph and pixel-wise annotations are automatically generated, overcoming human-biases and possible inconsistencies. We believe this dataset may encourage the exploration of original approaches to solve the anomaly detection task, e.g. by combining color, depth and normal maps, as they are not provided by most of the existing datasets. Indeed, in order to demonstrate how exploiting additional information may actually lead to higher detection performance, we show the results obtained by training a deep convolutional autoencoder to reconstruct different combinations of inputs.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85911542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-09DOI: 10.48550/arXiv.2210.04341
A. Fragomeni, Michael Wray, D. Damen
In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.
{"title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","authors":"A. Fragomeni, Michael Wray, D. Damen","doi":"10.48550/arXiv.2210.04341","DOIUrl":"https://doi.org/10.48550/arXiv.2210.04341","url":null,"abstract":"In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83359915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-09DOI: 10.48550/arXiv.2210.04369
Nicholas Rosa, T. Drummond, Mehrtash Harandi
Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the cost of extra computation, unstable adversarial optimisation or have losses on the feature space structure that are disconnected from fairness measures and only loosely generalise to fairness. In this work we propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model. Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training and directly improves the fairness of the regularised models. We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios, whilst still maintaining a high level of classification accuracy. Code is available at https://bitbucket.org/nelliottrosa/base_fairness.
{"title":"A Differentiable Distance Approximation for Fairer Image Classification","authors":"Nicholas Rosa, T. Drummond, Mehrtash Harandi","doi":"10.48550/arXiv.2210.04369","DOIUrl":"https://doi.org/10.48550/arXiv.2210.04369","url":null,"abstract":"Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the cost of extra computation, unstable adversarial optimisation or have losses on the feature space structure that are disconnected from fairness measures and only loosely generalise to fairness. In this work we propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model. Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training and directly improves the fairness of the regularised models. We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios, whilst still maintaining a high level of classification accuracy. Code is available at https://bitbucket.org/nelliottrosa/base_fairness.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73251253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-08DOI: 10.48550/arXiv.2210.03942
Hang Du, Xuejun Yan, Jingjing Wang, Di Xie, Shiliang Pu
Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a single-stage network, which makes it still challenging to generate a high-fidelity point distribution. Instead, upsampling point cloud in a coarse-to-fine manner is a decent solution. However, existing coarse-to-fine upsampling methods require extra training strategies, which are complicated and time-consuming during the training. In this paper, we propose a simple yet effective cascaded refinement network, consisting of three generation stages that have the same network architecture but achieve different objectives. Specifically, the first two upsampling stages generate the dense but coarse points progressively, while the last refinement stage further adjust the coarse points to a better position. To mitigate the learning conflicts between multiple stages and decrease the difficulty of regressing new points, we encourage each stage to predict the point offsets with respect to the input shape. In this manner, the proposed cascaded refinement network can be easily optimized without extra learning strategies. Moreover, we design a transformer-based feature extraction module to learn the informative global and local shape context. In inference phase, we can dynamically adjust the model efficiency and effectiveness, depending on the available computational resources. Extensive experiments on both synthetic and real-scanned datasets demonstrate that the proposed approach outperforms the existing state-of-the-art methods.
{"title":"Point Cloud Upsampling via Cascaded Refinement Network","authors":"Hang Du, Xuejun Yan, Jingjing Wang, Di Xie, Shiliang Pu","doi":"10.48550/arXiv.2210.03942","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03942","url":null,"abstract":"Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a single-stage network, which makes it still challenging to generate a high-fidelity point distribution. Instead, upsampling point cloud in a coarse-to-fine manner is a decent solution. However, existing coarse-to-fine upsampling methods require extra training strategies, which are complicated and time-consuming during the training. In this paper, we propose a simple yet effective cascaded refinement network, consisting of three generation stages that have the same network architecture but achieve different objectives. Specifically, the first two upsampling stages generate the dense but coarse points progressively, while the last refinement stage further adjust the coarse points to a better position. To mitigate the learning conflicts between multiple stages and decrease the difficulty of regressing new points, we encourage each stage to predict the point offsets with respect to the input shape. In this manner, the proposed cascaded refinement network can be easily optimized without extra learning strategies. Moreover, we design a transformer-based feature extraction module to learn the informative global and local shape context. In inference phase, we can dynamically adjust the model efficiency and effectiveness, depending on the available computational resources. Extensive experiments on both synthetic and real-scanned datasets demonstrate that the proposed approach outperforms the existing state-of-the-art methods.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76194086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-08DOI: 10.48550/arXiv.2210.03899
Jie Liu, Jingjing Wang, Peng Zhang, Chunmao Wang, Di Xie, Shiliang Pu
Currently, many face forgery detection methods aggregate spatial and frequency features to enhance the generalization ability and gain promising performance under the cross-dataset scenario. However, these methods only leverage one level frequency information which limits their expressive ability. To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection. Specifically, to take full advantage of the multi-scale and multi-frequency wavelet representation, we gradually aggregate the multi-scale wavelet representation at different stages of the backbone network. To better fuse the frequency feature with the spatial features, frequency-based spatial attention is designed to guide the spatial feature extractor to concentrate more on forgery traces. Meanwhile, cross-modality attention is proposed to fuse the frequency features with the spatial features. These two attention modules are calculated through a unified transformer block for efficiency. A wide variety of experiments demonstrate that the proposed method is efficient and effective for both within and cross datasets.
{"title":"Multi-Scale Wavelet Transformer for Face Forgery Detection","authors":"Jie Liu, Jingjing Wang, Peng Zhang, Chunmao Wang, Di Xie, Shiliang Pu","doi":"10.48550/arXiv.2210.03899","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03899","url":null,"abstract":"Currently, many face forgery detection methods aggregate spatial and frequency features to enhance the generalization ability and gain promising performance under the cross-dataset scenario. However, these methods only leverage one level frequency information which limits their expressive ability. To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection. Specifically, to take full advantage of the multi-scale and multi-frequency wavelet representation, we gradually aggregate the multi-scale wavelet representation at different stages of the backbone network. To better fuse the frequency feature with the spatial features, frequency-based spatial attention is designed to guide the spatial feature extractor to concentrate more on forgery traces. Meanwhile, cross-modality attention is proposed to fuse the frequency features with the spatial features. These two attention modules are calculated through a unified transformer block for efficiency. A wide variety of experiments demonstrate that the proposed method is efficient and effective for both within and cross datasets.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76415461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-07DOI: 10.48550/arXiv.2210.03433
M. Fiaz, Hisham Cholakkal, Sanath Narayan, R. Anwer, F. Khan
Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, the previous study focuses on rich feature information learning, it is still hard to retrieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention-aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a person and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by introducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervision or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHKSYSU and PRW. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5 in the mAP score over SeqNet, while operating at a comparable speed.
{"title":"PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search","authors":"M. Fiaz, Hisham Cholakkal, Sanath Narayan, R. Anwer, F. Khan","doi":"10.48550/arXiv.2210.03433","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03433","url":null,"abstract":"Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, the previous study focuses on rich feature information learning, it is still hard to retrieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention-aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a person and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by introducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervision or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHKSYSU and PRW. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5 in the mAP score over SeqNet, while operating at a comparable speed.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89310453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics. In this work, we propose a novel Focal and Global Spatial-Temporal Transformer network (FG-STFormer), that is equipped with two key components: (1) FG-SFormer: focal joints and global parts coupling spatial transformer. It forces the network to focus on modelling correlations for both the learned discriminative spatial joints and human body parts respectively. The selective focal joints eliminate the negative effect of non-informative ones during accumulating the correlations. Meanwhile, the interactions between the focal joints and body parts are incorporated to enhance the spatial dependencies via mutual cross-attention. (2) FG-TFormer: focal and global temporal transformer. Dilated temporal convolution is integrated into the global self-attention mechanism to explicitly capture the local temporal motion patterns of joints or body parts, which is found to be vital important to make temporal transformer work. Extensive experimental results on three benchmarks, namely NTU-60, NTU-120 and NW-UCLA, show our FG-STFormer surpasses all existing transformer-based methods, and compares favourably with state-of-the art GCN-based methods.
{"title":"Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition","authors":"Zhimin Gao, Peitao Wang, Pei Lv, Xiaoheng Jiang, Qi-dong Liu, Pichao Wang, Mingliang Xu, Wanqing Li","doi":"10.48550/arXiv.2210.02693","DOIUrl":"https://doi.org/10.48550/arXiv.2210.02693","url":null,"abstract":"Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics. In this work, we propose a novel Focal and Global Spatial-Temporal Transformer network (FG-STFormer), that is equipped with two key components: (1) FG-SFormer: focal joints and global parts coupling spatial transformer. It forces the network to focus on modelling correlations for both the learned discriminative spatial joints and human body parts respectively. The selective focal joints eliminate the negative effect of non-informative ones during accumulating the correlations. Meanwhile, the interactions between the focal joints and body parts are incorporated to enhance the spatial dependencies via mutual cross-attention. (2) FG-TFormer: focal and global temporal transformer. Dilated temporal convolution is integrated into the global self-attention mechanism to explicitly capture the local temporal motion patterns of joints or body parts, which is found to be vital important to make temporal transformer work. Extensive experimental results on three benchmarks, namely NTU-60, NTU-120 and NW-UCLA, show our FG-STFormer surpasses all existing transformer-based methods, and compares favourably with state-of-the art GCN-based methods.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88447890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-06DOI: 10.48550/arXiv.2210.02995
Olivia Wiles, J. Carreira, Iain Barr, Andrew Zisserman, Mateusz Malinowski
Experience and reasoning occur across multiple temporal scales: milliseconds, seconds, hours or days. The vast majority of computer vision research, however, still focuses on individual images or short videos lasting only a few seconds. This is because handling longer videos require more scalable approaches even to process them. In this work, we propose a framework enabling research on hour-long videos with the same hardware that can now process second-long videos. We replace standard video compression, e.g. JPEG, with neural compression and show that we can directly feed compressed videos as inputs to regular video networks. Operating on compressed videos improves efficiency at all pipeline levels -- data transfer, speed and memory -- making it possible to train models faster and on much longer videos. Processing compressed signals has, however, the downside of precluding standard augmentation techniques if done naively. We address that by introducing a small network that can apply transformations to latent codes corresponding to commonly used augmentations in the original video space. We demonstrate that with our compressed vision pipeline, we can train video models more efficiently on popular benchmarks such as Kinetics600 and COIN. We also perform proof-of-concept experiments with new tasks defined over hour-long videos at standard frame rates. Processing such long videos is impossible without using compressed representation.
{"title":"Compressed Vision for Efficient Video Understanding","authors":"Olivia Wiles, J. Carreira, Iain Barr, Andrew Zisserman, Mateusz Malinowski","doi":"10.48550/arXiv.2210.02995","DOIUrl":"https://doi.org/10.48550/arXiv.2210.02995","url":null,"abstract":"Experience and reasoning occur across multiple temporal scales: milliseconds, seconds, hours or days. The vast majority of computer vision research, however, still focuses on individual images or short videos lasting only a few seconds. This is because handling longer videos require more scalable approaches even to process them. In this work, we propose a framework enabling research on hour-long videos with the same hardware that can now process second-long videos. We replace standard video compression, e.g. JPEG, with neural compression and show that we can directly feed compressed videos as inputs to regular video networks. Operating on compressed videos improves efficiency at all pipeline levels -- data transfer, speed and memory -- making it possible to train models faster and on much longer videos. Processing compressed signals has, however, the downside of precluding standard augmentation techniques if done naively. We address that by introducing a small network that can apply transformations to latent codes corresponding to commonly used augmentations in the original video space. We demonstrate that with our compressed vision pipeline, we can train video models more efficiently on popular benchmarks such as Kinetics600 and COIN. We also perform proof-of-concept experiments with new tasks defined over hour-long videos at standard frame rates. Processing such long videos is impossible without using compressed representation.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87621842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-06DOI: 10.48550/arXiv.2210.03061
Yeying Jin, Wending Yan, Wenhan Yang, R. Tan
Few existing image defogging or dehazing methods consider dense and non-uniform particle distributions, which usually happen in smoke, dust and fog. Dealing with these dense and/or non-uniform distributions can be intractable, since fog's attenuation and airlight (or veiling effect) significantly weaken the background scene information in the input image. To address this problem, we introduce a structure-representation network with uncertainty feedback learning. Specifically, we extract the feature representations from a pre-trained Vision Transformer (DINO-ViT) module to recover the background information. To guide our network to focus on non-uniform fog areas, and then remove the fog accordingly, we introduce the uncertainty feedback learning, which produces the uncertainty maps, that have higher uncertainty in denser fog regions, and can be regarded as an attention map that represents fog's density and uneven distribution. Based on the uncertainty map, our feedback network refines our defogged output iteratively. Moreover, to handle the intractability of estimating the atmospheric light colors, we exploit the grayscale version of our input image, since it is less affected by varying light colors that are possibly present in the input image. The experimental results demonstrate the effectiveness of our method both quantitatively and qualitatively compared to the state-of-the-art methods in handling dense and non-uniform fog or smoke.
{"title":"Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal","authors":"Yeying Jin, Wending Yan, Wenhan Yang, R. Tan","doi":"10.48550/arXiv.2210.03061","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03061","url":null,"abstract":"Few existing image defogging or dehazing methods consider dense and non-uniform particle distributions, which usually happen in smoke, dust and fog. Dealing with these dense and/or non-uniform distributions can be intractable, since fog's attenuation and airlight (or veiling effect) significantly weaken the background scene information in the input image. To address this problem, we introduce a structure-representation network with uncertainty feedback learning. Specifically, we extract the feature representations from a pre-trained Vision Transformer (DINO-ViT) module to recover the background information. To guide our network to focus on non-uniform fog areas, and then remove the fog accordingly, we introduce the uncertainty feedback learning, which produces the uncertainty maps, that have higher uncertainty in denser fog regions, and can be regarded as an attention map that represents fog's density and uneven distribution. Based on the uncertainty map, our feedback network refines our defogged output iteratively. Moreover, to handle the intractability of estimating the atmospheric light colors, we exploit the grayscale version of our input image, since it is less affected by varying light colors that are possibly present in the input image. The experimental results demonstrate the effectiveness of our method both quantitatively and qualitatively compared to the state-of-the-art methods in handling dense and non-uniform fog or smoke.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91022873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}