It is challenging in learning a makeup-invariant face verification model, due to (1) insufficient makeup/non-makeup face training pairs, (2) the lack of diverse makeup faces, and (3) the significant appearance changes caused by cosmetics. To address these challenges, we propose a unified Face Morphological Multi-branch Network (FMMu-Net) for makeup-invariant face verification, which can simultaneously synthesize many diverse makeup faces through face morphology network (FM-Net) and effectively learn cosmetics-robust face representations using attention-based multi-branch learning network (AttM-Net). For challenges (1) and (2), FM-Net (two stacked auto-encoders) can synthesize realistic makeup face images by transferring specific regions of cosmetics via cycle consistent loss. For challenge (3), AttM-Net, consisting of one global and three local (task-driven on two eyes and mouth) branches, can effectively capture the complementary holistic and detailed information. Unlike DeepID2 which uses simple concatenation fusion, we introduce a heuristic method AttM-FM, attached to AttM-Net, to adaptively weight the features of different branches guided by the holistic information. We conduct extensive experiments on makeup face verification benchmarks (M-501, M-203, and FAM) and general face recognition datasets (LFW and IJB-A). Our framework FMMu-Net achieves state-of-the-art performances.
{"title":"FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification","authors":"Wenxuan Wang, Yanwei Fu, Xuelin Qian, Yu-Gang Jiang, Qi Tian, X. Xue","doi":"10.1109/cvpr42600.2020.00577","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00577","url":null,"abstract":"It is challenging in learning a makeup-invariant face verification model, due to (1) insufficient makeup/non-makeup face training pairs, (2) the lack of diverse makeup faces, and (3) the significant appearance changes caused by cosmetics. To address these challenges, we propose a unified Face Morphological Multi-branch Network (FMMu-Net) for makeup-invariant face verification, which can simultaneously synthesize many diverse makeup faces through face morphology network (FM-Net) and effectively learn cosmetics-robust face representations using attention-based multi-branch learning network (AttM-Net). For challenges (1) and (2), FM-Net (two stacked auto-encoders) can synthesize realistic makeup face images by transferring specific regions of cosmetics via cycle consistent loss. For challenge (3), AttM-Net, consisting of one global and three local (task-driven on two eyes and mouth) branches, can effectively capture the complementary holistic and detailed information. Unlike DeepID2 which uses simple concatenation fusion, we introduce a heuristic method AttM-FM, attached to AttM-Net, to adaptively weight the features of different branches guided by the holistic information. We conduct extensive experiments on makeup face verification benchmarks (M-501, M-203, and FAM) and general face recognition datasets (LFW and IJB-A). Our framework FMMu-Net achieves state-of-the-art performances.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"24 1","pages":"5729-5739"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90865609","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.01180
Sainan Liu, Vincent Nguyen, Isaac Rehg, Z. Tu
In this paper, we tackle an important task in computer vision: any view object recognition. In both training and testing, for each object instance, we are only given its 2D image viewed from an unknown angle. We propose a computational framework by designing object and viewer-centered neural networks (OVCNet) to recognize an object instance viewed from an arbitrary unknown angle. OVCNet consists of three branches that respectively implement object-centered, 3D viewer-centered, and in-plane viewer-centered recognition. We evaluate our proposed OVCNet using two metrics with unseen views from both seen and novel object instances. Experimental results demonstrate the advantages of OVCNet over classic 2D-image-based CNN classifiers, 3D-object (inferred from 2D image) classifiers, and competing multi-view based approaches. It gives rise to a viable and practical computing framework that combines both viewpoint-dependent and viewpoint-independent features for object recognition from any view.
{"title":"Recognizing Objects From Any View With Object and Viewer-Centered Representations","authors":"Sainan Liu, Vincent Nguyen, Isaac Rehg, Z. Tu","doi":"10.1109/cvpr42600.2020.01180","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.01180","url":null,"abstract":"In this paper, we tackle an important task in computer vision: any view object recognition. In both training and testing, for each object instance, we are only given its 2D image viewed from an unknown angle. We propose a computational framework by designing object and viewer-centered neural networks (OVCNet) to recognize an object instance viewed from an arbitrary unknown angle. OVCNet consists of three branches that respectively implement object-centered, 3D viewer-centered, and in-plane viewer-centered recognition. We evaluate our proposed OVCNet using two metrics with unseen views from both seen and novel object instances. Experimental results demonstrate the advantages of OVCNet over classic 2D-image-based CNN classifiers, 3D-object (inferred from 2D image) classifiers, and competing multi-view based approaches. It gives rise to a viable and practical computing framework that combines both viewpoint-dependent and viewpoint-independent features for object recognition from any view.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"2 1","pages":"11781-11790"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90114269","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.01189
Chenhang He, Huiyu Zeng, Jianqiang Huang, Xiansheng Hua, Lei Zhang
3D object detection from point cloud data plays an essential role in autonomous driving. Current single-stage detectors are efficient by progressively downscaling the 3D point clouds in a fully convolutional manner. However, the downscaled features inevitably lose spatial information and cannot make full use of the structure information of 3D point cloud, degrading their localization precision. In this work, we propose to improve the localization precision of single-stage detectors by explicitly leveraging the structure information of 3D point cloud. Specifically, we design an auxiliary network which converts the convolutional features in the backbone network back to point-level representations. The auxiliary network is jointly optimized, by two point-level supervisions, to guide the convolutional features in the backbone network to be aware of the object structure. The auxiliary network can be detached after training and therefore introduces no extra computation in the inference stage. Besides, considering that single-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient part-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed detector ranks at the top of KITTI 3D/BEV detection leaderboards and runs at 25 FPS for inference.
{"title":"Structure Aware Single-Stage 3D Object Detection From Point Cloud","authors":"Chenhang He, Huiyu Zeng, Jianqiang Huang, Xiansheng Hua, Lei Zhang","doi":"10.1109/cvpr42600.2020.01189","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.01189","url":null,"abstract":"3D object detection from point cloud data plays an essential role in autonomous driving. Current single-stage detectors are efficient by progressively downscaling the 3D point clouds in a fully convolutional manner. However, the downscaled features inevitably lose spatial information and cannot make full use of the structure information of 3D point cloud, degrading their localization precision. In this work, we propose to improve the localization precision of single-stage detectors by explicitly leveraging the structure information of 3D point cloud. Specifically, we design an auxiliary network which converts the convolutional features in the backbone network back to point-level representations. The auxiliary network is jointly optimized, by two point-level supervisions, to guide the convolutional features in the backbone network to be aware of the object structure. The auxiliary network can be detached after training and therefore introduces no extra computation in the inference stage. Besides, considering that single-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient part-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed detector ranks at the top of KITTI 3D/BEV detection leaderboards and runs at 25 FPS for inference.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"49 1","pages":"11870-11879"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90231944","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.01304
Junhang Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Q. Tian
To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution. To address this problem, we propose a label decoupling framework (LDF) which consists of a label decoupling (LD) procedure and a feature interaction network (FIN). LD explicitly decomposes the original saliency map into body map and detail map, where body map concentrates on center areas of objects and detail map focuses on regions around edges. Detail map works better because it involves much more pixels than traditional edge supervision. Different from saliency map, body map discards edge pixels and only pays attention to center areas. This successfully avoids the distraction from edge pixels during training. Therefore, we employ two branches in FIN to deal with body map and detail map respectively. Feature interaction (FI) is designed to fuse the two complementary branches to predict the saliency map, which is then used to refine the two branches again. This iterative refinement is helpful for learning better representations and more precise saliency maps. Comprehensive experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.
{"title":"Label Decoupling Framework for Salient Object Detection","authors":"Junhang Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Q. Tian","doi":"10.1109/cvpr42600.2020.01304","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.01304","url":null,"abstract":"To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution. To address this problem, we propose a label decoupling framework (LDF) which consists of a label decoupling (LD) procedure and a feature interaction network (FIN). LD explicitly decomposes the original saliency map into body map and detail map, where body map concentrates on center areas of objects and detail map focuses on regions around edges. Detail map works better because it involves much more pixels than traditional edge supervision. Different from saliency map, body map discards edge pixels and only pays attention to center areas. This successfully avoids the distraction from edge pixels during training. Therefore, we employ two branches in FIN to deal with body map and detail map respectively. Feature interaction (FI) is designed to fuse the two complementary branches to predict the saliency map, which is then used to refine the two branches again. This iterative refinement is helpful for learning better representations and more precise saliency maps. Comprehensive experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"10 1","pages":"13022-13031"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87607887","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.00556
B. Zhu, C. Ngo
This paper addresses the problem of text-to-image synthesis from a new perspective, i.e., the cause-and-effect chain in image generation. Causality is a common phenomenon in cooking. The dish appearance changes depending on the cooking actions and ingredients. The challenge of synthesis is that a generated image should depict the visual result of action-on-object. This paper presents a new network architecture, CookGAN, that mimics visual effect in causality chain, preserves fine-grained details and progressively upsamples image. Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a series of steps. Experiments on Recipe1M verify that CookGAN manages to generate food images with reasonably impressive inception score. Furthermore, the images are semantically interpretable and manipulable.
{"title":"CookGAN: Causality Based Text-to-Image Synthesis","authors":"B. Zhu, C. Ngo","doi":"10.1109/cvpr42600.2020.00556","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00556","url":null,"abstract":"This paper addresses the problem of text-to-image synthesis from a new perspective, i.e., the cause-and-effect chain in image generation. Causality is a common phenomenon in cooking. The dish appearance changes depending on the cooking actions and ingredients. The challenge of synthesis is that a generated image should depict the visual result of action-on-object. This paper presents a new network architecture, CookGAN, that mimics visual effect in causality chain, preserves fine-grained details and progressively upsamples image. Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a series of steps. Experiments on Recipe1M verify that CookGAN manages to generate food images with reasonably impressive inception score. Furthermore, the images are semantically interpretable and manipulable.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"5518-5526"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83678618","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 : 2020-06-01DOI: 10.1109/CVPR42600.2020.00263
Jinglei Shi, Xiaoran Jiang, C. Guillemot
In this paper, we present a learning-based framework for light field view synthesis from a subset of input views. Building upon a light-weight optical flow estimation network to obtain depth maps, our method employs two reconstruction modules in pixel and feature domains respectively. For the pixel-wise reconstruction, occlusions are explicitly handled by a disparity-dependent interpolation filter, whereas inpainting on disoccluded areas is learned by convolutional layers. Due to disparity inconsistencies, the pixel-based reconstruction may lead to blurriness in highly textured areas as well as on object contours. On the contrary, the feature-based reconstruction well performs on high frequencies, making the reconstruction in the two domains complementary. End-to-end learning is finally performed including a fusion module merging pixel and feature-based reconstructions. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world datasets, moreover, it is even able to extend light fields' baseline by extrapolating high quality views without additional training.
{"title":"Learning Fused Pixel and Feature-Based View Reconstructions for Light Fields","authors":"Jinglei Shi, Xiaoran Jiang, C. Guillemot","doi":"10.1109/CVPR42600.2020.00263","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.00263","url":null,"abstract":"In this paper, we present a learning-based framework for light field view synthesis from a subset of input views. Building upon a light-weight optical flow estimation network to obtain depth maps, our method employs two reconstruction modules in pixel and feature domains respectively. For the pixel-wise reconstruction, occlusions are explicitly handled by a disparity-dependent interpolation filter, whereas inpainting on disoccluded areas is learned by convolutional layers. Due to disparity inconsistencies, the pixel-based reconstruction may lead to blurriness in highly textured areas as well as on object contours. On the contrary, the feature-based reconstruction well performs on high frequencies, making the reconstruction in the two domains complementary. End-to-end learning is finally performed including a fusion module merging pixel and feature-based reconstructions. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world datasets, moreover, it is even able to extend light fields' baseline by extrapolating high quality views without additional training.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"10 1","pages":"2552-2561"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88097333","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.00151
Lin Zhu, Siwei Dong, Jianing Li, Tiejun Huang, Yonghong Tian
The high-sensitivity vision of primates, including humans, is mediated by a small retinal region called the fovea. As a novel bio-inspired vision sensor, spike camera mimics the fovea to record the nature scenes by continuous-time spikes instead of frame-based manner. However, reconstructing visual images from the spikes remains to be a challenge. In this paper, we design a retina-like visual image reconstruction framework, which is flexible in reconstructing full texture of natural scenes from the totally new spike data. Specifically, the proposed architecture consists of motion local excitation layer, spike refining layer and visual reconstruction layer motivated by bio-realistic leaky integrate and fire (LIF) neurons and synapse connection with spike-timing-dependent plasticity (STDP) rules. This approach may represent a major shift from conventional frame-based vision to the continuous-time retina-like vision, owning to the advantages of high temporal resolution and low power consumption. To test the performance, a spike dataset is constructed which is recorded by the spike camera. The experimental results show that the proposed approach is extremely effective in reconstructing the visual image in both normal and high speed scenes, while achieving high dynamic range and high image quality.
包括人类在内的灵长类动物的高灵敏度视觉是由一个叫做中央凹的小视网膜区域调节的。刺突相机是一种新型的仿生视觉传感器，它以连续时间的刺突代替基于帧的方式来模拟中央凹来记录自然场景。然而，从尖刺中重建视觉图像仍然是一个挑战。本文设计了一种类似视网膜的视觉图像重建框架，该框架可以灵活地从全新的峰值数据中重建自然场景的全纹理。具体而言，该结构由运动局部激励层、脉冲精炼层和视觉重建层组成，这些层由生物逼真的漏积分和火(LIF)神经元驱动，并根据spike- time -dependent plasticity (STDP)规则连接突触。该方法具有高时间分辨率和低功耗的优点，可能代表着从传统的基于框架的视觉到连续时间类视网膜视觉的重大转变。为了测试该算法的性能，构建了一个由spike摄像机记录的spike数据集。实验结果表明，该方法在正常和高速场景下都能非常有效地重建视觉图像，同时实现高动态范围和高图像质量。
{"title":"Retina-Like Visual Image Reconstruction via Spiking Neural Model","authors":"Lin Zhu, Siwei Dong, Jianing Li, Tiejun Huang, Yonghong Tian","doi":"10.1109/cvpr42600.2020.00151","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00151","url":null,"abstract":"The high-sensitivity vision of primates, including humans, is mediated by a small retinal region called the fovea. As a novel bio-inspired vision sensor, spike camera mimics the fovea to record the nature scenes by continuous-time spikes instead of frame-based manner. However, reconstructing visual images from the spikes remains to be a challenge. In this paper, we design a retina-like visual image reconstruction framework, which is flexible in reconstructing full texture of natural scenes from the totally new spike data. Specifically, the proposed architecture consists of motion local excitation layer, spike refining layer and visual reconstruction layer motivated by bio-realistic leaky integrate and fire (LIF) neurons and synapse connection with spike-timing-dependent plasticity (STDP) rules. This approach may represent a major shift from conventional frame-based vision to the continuous-time retina-like vision, owning to the advantages of high temporal resolution and low power consumption. To test the performance, a spike dataset is constructed which is recorded by the spike camera. The experimental results show that the proposed approach is extremely effective in reconstructing the visual image in both normal and high speed scenes, while achieving high dynamic range and high image quality.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"14 1","pages":"1435-1443"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87329231","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 : 2020-06-01DOI: 10.1109/CVPR42600.2020.01472
Mohamed Yousef, Tom E. Bishop
Text recognition is a major computer vision task with a big set of associated challenges. One of those traditional challenges is the coupled nature of text recognition and segmentation. This problem has been progressively solved over the past decades, going from segmentation based recognition to segmentation free approaches, which proved more accurate and much cheaper to annotate data for. We take a step from segmentation-free single line recognition towards segmentation-free multi-line / full page recognition. We propose a novel and simple neural network module, termed OrigamiNet, that can augment any CTC-trained, fully convolutional single line text recognizer, to convert it into a multi-line version by providing the model with enough spatial capacity to be able to properly collapse a 2D input signal into 1D without losing information. Such modified networks can be trained using exactly their same simple original procedure, and using only unsegmented image and text pairs. We carry out a set of interpretability experiments that show that our trained models learn an accurate implicit line segmentation. We achieve state-of-the-art character error rate on both IAM & ICDAR 2017 HTR benchmarks for handwriting recognition, surpassing all other methods in the literature. On IAM we even surpass single line methods that use accurate localization information during training. Our code is available online at https://github.com/IntuitionMachines/OrigamiNet .
{"title":"OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold","authors":"Mohamed Yousef, Tom E. Bishop","doi":"10.1109/CVPR42600.2020.01472","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.01472","url":null,"abstract":"Text recognition is a major computer vision task with a big set of associated challenges. One of those traditional challenges is the coupled nature of text recognition and segmentation. This problem has been progressively solved over the past decades, going from segmentation based recognition to segmentation free approaches, which proved more accurate and much cheaper to annotate data for. We take a step from segmentation-free single line recognition towards segmentation-free multi-line / full page recognition. We propose a novel and simple neural network module, termed OrigamiNet, that can augment any CTC-trained, fully convolutional single line text recognizer, to convert it into a multi-line version by providing the model with enough spatial capacity to be able to properly collapse a 2D input signal into 1D without losing information. Such modified networks can be trained using exactly their same simple original procedure, and using only unsegmented image and text pairs. We carry out a set of interpretability experiments that show that our trained models learn an accurate implicit line segmentation. We achieve state-of-the-art character error rate on both IAM & ICDAR 2017 HTR benchmarks for handwriting recognition, surpassing all other methods in the literature. On IAM we even surpass single line methods that use accurate localization information during training. Our code is available online at https://github.com/IntuitionMachines/OrigamiNet .","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"9 1","pages":"14698-14707"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87470566","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 : 2020-06-01DOI: 10.1109/cvpr42600.2020.00835
Qiangchang Wang, Tianyi Wu, He Zheng, G. Guo
Deep learning has achieved a great success in face recognition (FR), however, few existing models take hierarchical multi-scale local features into consideration. In this work, we propose a hierarchical pyramid diverse attention (HPDA) network. First, it is observed that local patches would play important roles in FR when the global face appearance changes dramatically. Some recent works apply attention modules to locate local patches automatically without relying on face landmarks. Unfortunately, without considering diversity, some learned attentions tend to have redundant responses around some similar local patches, while neglecting other potential discriminative facial parts. Meanwhile, local patches may appear at different scales due to pose variations or large expression changes. To alleviate these challenges, we propose a pyramid diverse attention (PDA) to learn multi-scale diverse local representations automatically and adaptively. More specifically, a pyramid attention is developed to capture multi-scale features. Meanwhile, a diverse learning is developed to encourage models to focus on different local patches and generate diverse local features. Second, almost all existing models focus on extracting features from the last convolutional layer, lacking of local details or small-scale face parts in lower layers. Instead of simple concatenation or addition, we propose to use a hierarchical bilinear pooling (HBP) to fuse information from multiple layers effectively. Thus, the HPDA is developed by integrating the PDA into the HBP. Experimental results on several datasets show the effectiveness of the HPDA, compared to the state-of-the-art methods.
{"title":"Hierarchical Pyramid Diverse Attention Networks for Face Recognition","authors":"Qiangchang Wang, Tianyi Wu, He Zheng, G. Guo","doi":"10.1109/cvpr42600.2020.00835","DOIUrl":"https://doi.org/10.1109/cvpr42600.2020.00835","url":null,"abstract":"Deep learning has achieved a great success in face recognition (FR), however, few existing models take hierarchical multi-scale local features into consideration. In this work, we propose a hierarchical pyramid diverse attention (HPDA) network. First, it is observed that local patches would play important roles in FR when the global face appearance changes dramatically. Some recent works apply attention modules to locate local patches automatically without relying on face landmarks. Unfortunately, without considering diversity, some learned attentions tend to have redundant responses around some similar local patches, while neglecting other potential discriminative facial parts. Meanwhile, local patches may appear at different scales due to pose variations or large expression changes. To alleviate these challenges, we propose a pyramid diverse attention (PDA) to learn multi-scale diverse local representations automatically and adaptively. More specifically, a pyramid attention is developed to capture multi-scale features. Meanwhile, a diverse learning is developed to encourage models to focus on different local patches and generate diverse local features. Second, almost all existing models focus on extracting features from the last convolutional layer, lacking of local details or small-scale face parts in lower layers. Instead of simple concatenation or addition, we propose to use a hierarchical bilinear pooling (HBP) to fuse information from multiple layers effectively. Thus, the HPDA is developed by integrating the PDA into the HBP. Experimental results on several datasets show the effectiveness of the HPDA, compared to the state-of-the-art methods.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"8323-8332"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88294079","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 : 2020-06-01DOI: 10.1109/CVPR42600.2020.01066
Josip Saric, Marin Orsic, Tonci Antunovic, Sacha Vrazic, Sinisa Segvic
We address anticipation of scene development by forecasting semantic segmentation of future frames. Several previous works approach this problem by F2F (feature-to-feature) forecasting where future features are regressed from observed features. Different from previous work, we consider a novel F2M (feature-to-motion) formulation, which performs the forecast by warping observed features according to regressed feature flow. This formulation models a causal relationship between the past and the future, and regularizes inference by reducing dimensionality of the forecasting target. However, emergence of future scenery which was not visible in observed frames can not be explained by warping. We propose to address this issue by complementing F2M forecasting with the classic F2F approach. We realize this idea as a multi-head F2MF model built atop shared features. Experiments show that the F2M head prevails in static parts of the scene while the F2F head kicks-in to fill-in the novel regions. The proposed F2MF model operates in synergy with correlation features and outperforms all previous approaches both in short-term and mid-term forecast on the Cityscapes dataset.
{"title":"Warp to the Future: Joint Forecasting of Features and Feature Motion","authors":"Josip Saric, Marin Orsic, Tonci Antunovic, Sacha Vrazic, Sinisa Segvic","doi":"10.1109/CVPR42600.2020.01066","DOIUrl":"https://doi.org/10.1109/CVPR42600.2020.01066","url":null,"abstract":"We address anticipation of scene development by forecasting semantic segmentation of future frames. Several previous works approach this problem by F2F (feature-to-feature) forecasting where future features are regressed from observed features. Different from previous work, we consider a novel F2M (feature-to-motion) formulation, which performs the forecast by warping observed features according to regressed feature flow. This formulation models a causal relationship between the past and the future, and regularizes inference by reducing dimensionality of the forecasting target. However, emergence of future scenery which was not visible in observed frames can not be explained by warping. We propose to address this issue by complementing F2M forecasting with the classic F2F approach. We realize this idea as a multi-head F2MF model built atop shared features. Experiments show that the F2M head prevails in static parts of the scene while the F2F head kicks-in to fill-in the novel regions. The proposed F2MF model operates in synergy with correlation features and outperforms all previous approaches both in short-term and mid-term forecast on the Cityscapes dataset.","PeriodicalId":6715,"journal":{"name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"78 1","pages":"10645-10654"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88647808","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：