Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

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.

arXiv commentNeurIPS 2021

References in corpus (13)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• The information bottleneck method
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Opening the Black Box of Deep Neural Networks via Information
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
• Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
• Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
• Robust Tumor Localization with Pyramid Grad-CAM
• Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
• Weakly-Supervised Semantic Segmentation via Sub-category Exploration