Self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated images. Compared with photographic images, medical images acquired with the same imaging protocol exhibit high consistency in anatomy. To exploit this anatomical consistency, this paper introduces a novel SSL approach, called PEAC (patch embedding of anatomical consistency), for medical image analysis. Specifically, in this paper, we propose to learn global and local consistencies via stable grid-based matching, transfer pre-trained PEAC models to diverse downstream tasks, and extensively demonstrate that (1) PEAC achieves significantly better performance than the existing state-of-the-art fully/self-supervised methods, and (2) PEAC captures the anatomical structure consistency across views of the same patient and across patients of different genders, weights, and healthy statuses, which enhances the interpretability of our method for medical image analysis. All code and pretrained models are available at GitHub.com/JLiangLab/PEAC.
{"title":"Learning Anatomically Consistent Embedding for Chest Radiography.","authors":"Ziyu Zhou, Haozhe Luo, Jiaxuan Pang, Xiaowei Ding, Michael Gotway, Jianming Liang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated images. Compared with photographic images, medical images acquired with the same imaging protocol exhibit high consistency in anatomy. To exploit this anatomical consistency, this paper introduces a novel SSL approach, called PEAC (patch embedding of anatomical consistency), for medical image analysis. Specifically, in this paper, we propose to learn global and local consistencies via stable grid-based matching, transfer pre-trained PEAC models to diverse downstream tasks, and extensively demonstrate that (1) PEAC achieves significantly better performance than the existing state-of-the-art fully/self-supervised methods, and (2) PEAC captures the anatomical structure consistency across views of the same patient and across patients of different genders, weights, and healthy statuses, which enhances the interpretability of our method for medical image analysis. All code and pretrained models are available at GitHub.com/JLiangLab/PEAC.</p>","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"2023 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11135486/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141174538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1007/s11263-023-01867-x
S. Koskinen, Erman Acar, Joni-Kristian Kämäräinen
{"title":"Single Pixel Spectral Color Constancy","authors":"S. Koskinen, Erman Acar, Joni-Kristian Kämäräinen","doi":"10.1007/s11263-023-01867-x","DOIUrl":"https://doi.org/10.1007/s11263-023-01867-x","url":null,"abstract":"","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"58 1","pages":"326"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91172866","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 : 2023-05-30DOI: 10.48550/arXiv.2305.18812
Qiang Wang, Di Kong, Fengyin Lin, Yonggang Qi
Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging. Traditionally, creating a deep learning model for sketch-to-image synthesis needs to overcome the distorted input sketch without visual details, and requires to collect large-scale sketch-image datasets. We first study this task by using diffusion models. Our model matches sketches through the cross domain constraints, and uses a classifier to guide the image synthesis more accurately. Extensive experiments confirmed that our method can not only be faithful to user's input sketches, but also maintain the diversity and imagination of synthetic image results. Our model can beat GAN-based method in terms of generation quality and human evaluation, and does not rely on massive sketch-image datasets. Additionally, we present applications of our method in image editing and interpolation.
{"title":"DiffSketching: Sketch Control Image Synthesis with Diffusion Models","authors":"Qiang Wang, Di Kong, Fengyin Lin, Yonggang Qi","doi":"10.48550/arXiv.2305.18812","DOIUrl":"https://doi.org/10.48550/arXiv.2305.18812","url":null,"abstract":"Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging. Traditionally, creating a deep learning model for sketch-to-image synthesis needs to overcome the distorted input sketch without visual details, and requires to collect large-scale sketch-image datasets. We first study this task by using diffusion models. Our model matches sketches through the cross domain constraints, and uses a classifier to guide the image synthesis more accurately. Extensive experiments confirmed that our method can not only be faithful to user's input sketches, but also maintain the diversity and imagination of synthetic image results. Our model can beat GAN-based method in terms of generation quality and human evaluation, and does not rely on massive sketch-image datasets. Additionally, we present applications of our method in image editing and interpolation.","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"129 1","pages":"67"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76692642","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 : 2023-02-16DOI: 10.48550/arXiv.2302.08366
Ruyu Wang, Sabrina Hoppe, Eduardo Monari, Marco F. Huber
Data-hunger and data-imbalance are two major pitfalls in many deep learning approaches. For example, on highly optimized production lines, defective samples are hardly acquired while non-defective samples come almost for free. The defects however often seem to resemble each other, e.g., scratches on different products may only differ in a few characteristics. In this work, we introduce a framework, Defect Transfer GAN (DT-GAN), which learns to represent defect types independent of and across various background products and yet can apply defect-specific styles to generate realistic defective images. An empirical study on the MVTec AD and two additional datasets showcase DT-GAN outperforms state-of-the-art image synthesis methods w.r.t. sample fidelity and diversity in defect generation. We further demonstrate benefits for a critical downstream task in manufacturing -- defect classification. Results show that the augmented data from DT-GAN provides consistent gains even in the few samples regime and reduces the error rate up to 51% compared to both traditional and advanced data augmentation methods.
{"title":"Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation","authors":"Ruyu Wang, Sabrina Hoppe, Eduardo Monari, Marco F. Huber","doi":"10.48550/arXiv.2302.08366","DOIUrl":"https://doi.org/10.48550/arXiv.2302.08366","url":null,"abstract":"Data-hunger and data-imbalance are two major pitfalls in many deep learning approaches. For example, on highly optimized production lines, defective samples are hardly acquired while non-defective samples come almost for free. The defects however often seem to resemble each other, e.g., scratches on different products may only differ in a few characteristics. In this work, we introduce a framework, Defect Transfer GAN (DT-GAN), which learns to represent defect types independent of and across various background products and yet can apply defect-specific styles to generate realistic defective images. An empirical study on the MVTec AD and two additional datasets showcase DT-GAN outperforms state-of-the-art image synthesis methods w.r.t. sample fidelity and diversity in defect generation. We further demonstrate benefits for a critical downstream task in manufacturing -- defect classification. Results show that the augmented data from DT-GAN provides consistent gains even in the few samples regime and reduces the error rate up to 51% compared to both traditional and advanced data augmentation methods.","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"7 1","pages":"445"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89106587","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}
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness of transformers applied to computer vision and benchmark several bias mitigation approaches from prior work. We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix. With this knowledge, we propose TADeT, a targeted alignment strategy for debiasing transformers that aims to discover and remove bias primarily from query matrix features. We measure performance using Balanced Accuracy and Standard Accuracy, and fairness using Equalized Odds and Balanced Accuracy Difference. TADeT consistently leads to improved fairness over prior work on multiple attribute prediction tasks on the CelebA dataset, without compromising performance.
{"title":"Mitigating Bias in Visual Transformers via Targeted Alignment","authors":"Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar, Judy Hoffman","doi":"10.48550/arXiv.2302.04358","DOIUrl":"https://doi.org/10.48550/arXiv.2302.04358","url":null,"abstract":"As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness of transformers applied to computer vision and benchmark several bias mitigation approaches from prior work. We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix. With this knowledge, we propose TADeT, a targeted alignment strategy for debiasing transformers that aims to discover and remove bias primarily from query matrix features. We measure performance using Balanced Accuracy and Standard Accuracy, and fairness using Equalized Odds and Balanced Accuracy Difference. TADeT consistently leads to improved fairness over prior work on multiple attribute prediction tasks on the CelebA dataset, without compromising performance.","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"25 1","pages":"138"},"PeriodicalIF":0.0,"publicationDate":"2023-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86601650","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 : 2023-02-01DOI: 10.48550/arXiv.2302.00178
Anthony Manchin, J. Sherrah, Qi Wu, A. Hengel
The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically presented difficulties for machines to grasp, especially when requiring computer vision. In this paper, we propose a model that can extract general rules from video demonstrations by simultaneously performing summarisation and translation. Our approach differs from prior works by framing the problem as a multi-sequence-to-sequence task, wherein summarisation is learnt by the model. This allows our model to utilise edge cases that would otherwise be suppressed or discarded by traditional summarisation techniques. Additionally, we show that our approach can handle noisy specifications without the need for additional filtering methods. We evaluate our model by synthesising programs from video demonstrations in the Vizdoom environment achieving state-of-the-art results with a relative increase of 11.75% program accuracy on prior works
{"title":"Program Generation from Diverse Video Demonstrations","authors":"Anthony Manchin, J. Sherrah, Qi Wu, A. Hengel","doi":"10.48550/arXiv.2302.00178","DOIUrl":"https://doi.org/10.48550/arXiv.2302.00178","url":null,"abstract":"The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically presented difficulties for machines to grasp, especially when requiring computer vision. In this paper, we propose a model that can extract general rules from video demonstrations by simultaneously performing summarisation and translation. Our approach differs from prior works by framing the problem as a multi-sequence-to-sequence task, wherein summarisation is learnt by the model. This allows our model to utilise edge cases that would otherwise be suppressed or discarded by traditional summarisation techniques. Additionally, we show that our approach can handle noisy specifications without the need for additional filtering methods. We evaluate our model by synthesising programs from video demonstrations in the Vizdoom environment achieving state-of-the-art results with a relative increase of 11.75% program accuracy on prior works","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"82 1","pages":"1039"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79962771","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 : 2023-01-25DOI: 10.48550/arXiv.2301.10413
Yerim Jung, Nur Suriza Syazwany, Sang-Chul Lee
Local feature matching is essential for many applications, such as localization and 3D reconstruction. However, it is challenging to match feature points accurately in various camera viewpoints and illumination conditions. In this paper, we propose a framework that robustly extracts and describes salient local features regardless of changing light and viewpoints. The framework suppresses illumination variations and encourages structural information to ignore the noise from light and to focus on edges. We classify the elements in the feature covariance matrix, an implicit feature map information, into two components. Our model extracts feature points from salient regions leading to reduced incorrect matches. In our experiments, the proposed method achieved higher accuracy than the state-of-the-art methods in the public dataset, such as HPatches, Aachen Day-Night, and ETH, which especially show highly variant viewpoints and illumination.
{"title":"Local Feature Extraction from Salient Regions by Feature Map Transformation","authors":"Yerim Jung, Nur Suriza Syazwany, Sang-Chul Lee","doi":"10.48550/arXiv.2301.10413","DOIUrl":"https://doi.org/10.48550/arXiv.2301.10413","url":null,"abstract":"Local feature matching is essential for many applications, such as localization and 3D reconstruction. However, it is challenging to match feature points accurately in various camera viewpoints and illumination conditions. In this paper, we propose a framework that robustly extracts and describes salient local features regardless of changing light and viewpoints. The framework suppresses illumination variations and encourages structural information to ignore the noise from light and to focus on edges. We classify the elements in the feature covariance matrix, an implicit feature map information, into two components. Our model extracts feature points from salient regions leading to reduced incorrect matches. In our experiments, the proposed method achieved higher accuracy than the state-of-the-art methods in the public dataset, such as HPatches, Aachen Day-Night, and ETH, which especially show highly variant viewpoints and illumination.","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"24 1","pages":"552"},"PeriodicalIF":0.0,"publicationDate":"2023-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86380460","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 : 2023-01-09DOI: 10.48550/arXiv.2301.03194
Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, J. Sonke, E. Gavves
Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query to tackle FSS. However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction. To this end, we propose a Support-induced Graph Convolutional Network (SiGCN) to explicitly excavate latent context structure in query images. Specifically, we propose a Support-induced Graph Reasoning (SiGR) module to capture salient query object parts at different semantic levels with a Support-induced GCN. Furthermore, an instance association (IA) module is designed to capture high-order instance context from both support and query instances. By integrating the proposed two modules, SiGCN can learn rich query context representation, and thus being more robust to appearance variations. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our SiGCN achieves state-of-the-art performance.
{"title":"Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network","authors":"Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, J. Sonke, E. Gavves","doi":"10.48550/arXiv.2301.03194","DOIUrl":"https://doi.org/10.48550/arXiv.2301.03194","url":null,"abstract":"Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query to tackle FSS. However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction. To this end, we propose a Support-induced Graph Convolutional Network (SiGCN) to explicitly excavate latent context structure in query images. Specifically, we propose a Support-induced Graph Reasoning (SiGR) module to capture salient query object parts at different semantic levels with a Support-induced GCN. Furthermore, an instance association (IA) module is designed to capture high-order instance context from both support and query instances. By integrating the proposed two modules, SiGCN can learn rich query context representation, and thus being more robust to appearance variations. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our SiGCN achieves state-of-the-art performance.","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"40 1","pages":"126"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74616690","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 : 2023-01-08DOI: 10.48550/arXiv.2301.03033
Zhengyi Liu, liuzywen
Crowd counting aims to estimate the number of persons in a scene. Most state-of-the-art crowd counting methods based on color images can't work well in poor illumination conditions due to invisible objects. With the widespread use of infrared cameras, crowd counting based on color and thermal images is studied. Existing methods only achieve multi-modal fusion without count objective constraint. To better excavate multi-modal information, we use count-guided multi-modal fusion and modal-guided count enhancement to achieve the impressive performance. The proposed count-guided multi-modal fusion module utilizes a multi-scale token transformer to interact two-modal information under the guidance of count information and perceive different scales from the token perspective. The proposed modal-guided count enhancement module employs multi-scale deformable transformer decoder structure to enhance one modality feature and count information by the other modality. Experiment in public RGBT-CC dataset shows that our method refreshes the state-of-the-art results. https://github.com/liuzywen/RGBTCC
{"title":"RGB-T Multi-Modal Crowd Counting Based on Transformer","authors":"Zhengyi Liu, liuzywen","doi":"10.48550/arXiv.2301.03033","DOIUrl":"https://doi.org/10.48550/arXiv.2301.03033","url":null,"abstract":"Crowd counting aims to estimate the number of persons in a scene. Most state-of-the-art crowd counting methods based on color images can't work well in poor illumination conditions due to invisible objects. With the widespread use of infrared cameras, crowd counting based on color and thermal images is studied. Existing methods only achieve multi-modal fusion without count objective constraint. To better excavate multi-modal information, we use count-guided multi-modal fusion and modal-guided count enhancement to achieve the impressive performance. The proposed count-guided multi-modal fusion module utilizes a multi-scale token transformer to interact two-modal information under the guidance of count information and perceive different scales from the token perspective. The proposed modal-guided count enhancement module employs multi-scale deformable transformer decoder structure to enhance one modality feature and count information by the other modality. Experiment in public RGBT-CC dataset shows that our method refreshes the state-of-the-art results. https://github.com/liuzywen/RGBTCC","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"35 1","pages":"427"},"PeriodicalIF":0.0,"publicationDate":"2023-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75632368","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 : 2023-01-04DOI: 10.48550/arXiv.2301.01531
Razvan Caramalau, Binod Bhattarai, D. Stoyanov, Tae-Kyun Kim
Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods. Code available: https://github.com/razvancaramalau/MoBYv2AL
{"title":"MoBYv2AL: Self-supervised Active Learning for Image Classification","authors":"Razvan Caramalau, Binod Bhattarai, D. Stoyanov, Tae-Kyun Kim","doi":"10.48550/arXiv.2301.01531","DOIUrl":"https://doi.org/10.48550/arXiv.2301.01531","url":null,"abstract":"Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods. Code available: https://github.com/razvancaramalau/MoBYv2AL","PeriodicalId":72437,"journal":{"name":"BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference","volume":"358 1","pages":"674"},"PeriodicalIF":0.0,"publicationDate":"2023-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76518513","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号