Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2110.06530v1
• Date: Wed, 13 Oct 2021 06:49:45 GMT
• Title: Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
• Authors: Jungbeom Lee, Jooyoung Choi, Jisoo Mok, Sungroh Yoon
• Abstract summary: Weakly supervised semantic segmentation produces pixel-level localization from class labels. A classifier trained on such labels is likely to focus on a small discriminative region of the target object. We propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification.
• Score: 17.979336178991083
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. We first support this argument through a simulated toy experiment and then propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification. Our experimental evaluations demonstrate that this simple modification significantly improves the quality of localization maps on both the PASCAL VOC 2012 and MS COCO 2014 datasets, exhibiting a new state-of-the-art performance for weakly supervised semantic segmentation. The code is available at: https://github.com/jbeomlee93/RIB.

Related papers

• Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label [7.400926717561454]
  This paper investigates a framework for weakly-supervised object localization. It aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels.
  arXiv  Detail & Related papers  (2024-04-15T06:02:09Z)
• Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation [84.62067728093358]
  Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. New paradigm has emerged by generating a foreground prediction map to achieve pixel-level localization. This paper presents two astonishing experimental observations on the object localization learning process.
  arXiv  Detail & Related papers  (2023-09-22T15:44:10Z)
• FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization [10.08410402383604]
  This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL) The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to localize previously learned classes. We first present a strong baseline method for CI-WSOL by adapting the strategies of class-incremental classifiers to catastrophic forgetting. We then propose the feature drift compensation network to compensate for the effects of feature drifts on class scores and localization maps.
  arXiv  Detail & Related papers  (2023-09-17T01:10:45Z)
• Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization [31.69344455448125]
  We present an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object.
  arXiv  Detail & Related papers  (2022-04-11T06:18:02Z)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels [55.049347205603304]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2021-11-19T10:15:22Z)
• Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation [64.2719590819468]
  We propose a non-salient region object mining approach for weakly supervised semantic segmentation. A potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region.
  arXiv  Detail & Related papers  (2021-03-26T16:44:03Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)
• SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor [51.298760338410624]
  We propose a SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information. The module predicts a scene descriptor, which learns to represent the categories of objects existing in the scene. We also design a region similarity loss to propagate distinguishing features to their own neighboring points with the same label.
  arXiv  Detail & Related papers  (2020-01-24T16:53:30Z)

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.