Extracting Class Activation Maps from Non-Discriminative Features as well

• URL: http://arxiv.org/abs/2303.10334v1
• Date: Sat, 18 Mar 2023 04:47:42 GMT
• Title: Extracting Class Activation Maps from Non-Discriminative Features as well
• Authors: Zhaozheng Chen and Qianru Sun
• Abstract summary: Class activation maps (CAM) from a classification model often results in poor coverage on foreground objects. We introduce a new computation method for CAM that explicitly captures non-discriminative features as well. We call the resultant K cluster centers local prototypes - represent local semantics like the "head", "leg", and "body" of "sheep"
• Score: 23.968856513180032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the "head" of "sheep") is recognized and the rest (e.g., the "leg" of "sheep") mistakenly as background. The crux behind is that the weight of the classifier (used to compute CAM) captures only the discriminative features of objects. We tackle this by introducing a new computation method for CAM that explicitly captures non-discriminative features as well, thereby expanding CAM to cover whole objects. Specifically, we omit the last pooling layer of the classification model, and perform clustering on all local features of an object class, where "local" means "at a spatial pixel position". We call the resultant K cluster centers local prototypes - represent local semantics like the "head", "leg", and "body" of "sheep". Given a new image of the class, we compare its unpooled features to every prototype, derive K similarity matrices, and then aggregate them into a heatmap (i.e., our CAM). Our CAM thus captures all local features of the class without discrimination. We evaluate it in the challenging tasks of weakly-supervised semantic segmentation (WSSS), and plug it in multiple state-of-the-art WSSS methods, such as MCTformer and AMN, by simply replacing their original CAM with ours. Our extensive experiments on standard WSSS benchmarks (PASCAL VOC and MS COCO) show the superiority of our method: consistent improvements with little computational overhead.

Related papers

• High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation [17.804090651425955]
  Image-level weakly-supervised segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss. We reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method.
  arXiv  Detail & Related papers  (2023-04-05T17:43:57Z)
• Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation [59.24824050194334]
  This paper turns to an interesting working mechanism in agent learning named Complementary Learning System ( CLS) Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) GSLM develops a General Learning Module (GLM) and a Specific Learning Module (SLM)
  arXiv  Detail & Related papers  (2023-03-04T16:16:47Z)
• Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation [98.306533433627]
  extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS) This paper proposes a new method to couple CAM and Attention matrix in a probabilistic Diffusion way, and dub it AD-CAM. Experiments show that AD-CAM as pseudo labels can yield stronger WSSS models than the state-of-the-art variants of CAM.
  arXiv  Detail & Related papers  (2022-11-20T10:06:32Z)
• Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation [66.87777732230884]
  We propose a saliency guided Inter- and Intra-Class Relation Constrained (I$2$CRC) framework to assist the expansion of the activated object regions. We also introduce an object guided label refinement module to take a full use of both the segmentation prediction and the initial labels for obtaining superior pseudo-labels.
  arXiv  Detail & Related papers  (2022-06-20T03:40:56Z)
• Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization [39.63778214094173]
  Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. We find the gap between classification and localization in terms of the misalignment of the directions between an input feature and a class-specific weight. We propose a method to align feature directions with a class-specific weight to bridge the gap.
  arXiv  Detail & Related papers  (2022-04-01T05:49:22Z)
• Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation [32.76127086403596]
  We propose Contrastive learning for Class-agnostic Activation Map (C$2$AM) generation using unlabeled image data. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions.
  arXiv  Detail & Related papers  (2022-03-25T08:46:24Z)
• Importance Sampling CAMs for Weakly-Supervised Segmentation [16.86352815414646]
  Class activation maps (CAMs) can be used to localize and segment objects in images by means of class activation maps (CAMs) In this work, we approach both problems with two contributions for improving CAM learning. We conduct experiments on the PASCAL VOC 2012 benchmark dataset to demonstrate that these modifications significantly increase the performance in terms of contour accuracy.
  arXiv  Detail & Related papers  (2022-03-23T14:54:29Z)
• Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation [72.33139350241044]
  Weakly Supervised Semantic COCO (WSSS) based on image-level labels has attracted much attention due to low annotation costs. We propose a Self-supervised Image-specific Prototype Exploration (SIPE) that consists of an Image-specific Prototype Exploration (IPE) and a General-Specific Consistency (GSC) loss. Our SIPE achieves new state-of-the-art performance using only image-level labels.
  arXiv  Detail & Related papers  (2022-03-06T09:01:03Z)
• Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation [88.55040177178442]
  Class activation maps (CAM) is arguably the most standard step of generating pseudo masks for semantic segmentation. Yet, the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. We introduce an embarrassingly simple yet surprisingly effective method: Reactivating the converged CAM with BCE by using softmax cross-entropy loss (SCE) The evaluation on both PASCAL VOC and MSCOCO shows that ReCAM not only generates high-quality masks, but also supports plug-and-play in any CAM variant with little overhead.
  arXiv  Detail & Related papers  (2022-03-02T09:14:58Z)
• Towards Learning Spatially Discriminative Feature Representations [26.554140976236052]
  We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature maps with the class activation maps (CAMs) CAM-loss drives the backbone to express the features of target category and suppress the features of non-target categories or background. Experimental results show that CAM-loss is applicable to a variety of network structures and can be combined with mainstream regularization methods to improve the performance of image classification.
  arXiv  Detail & Related papers  (2021-09-03T08:04:17Z)
• Conditional Variational Capsule Network for Open Set Recognition [64.18600886936557]
  In open set recognition, a classifier has to detect unknown classes that are not known at training time. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition. In our proposal, during training, capsules features of the same known class are encouraged to match a pre-defined gaussian, one for each class.
  arXiv  Detail & Related papers  (2021-04-19T09:39:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.