Importance Sampling CAMs for Weakly-Supervised Segmentation
arXiv:2203.12459 · doi:10.1109/ICASSP43922.2022.9746641
Abstract
Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs). However, without pixel-level annotations, classification networks are known to (1) mainly focus on discriminative regions, and (2) to produce diffuse CAMs without well-defined prediction contours. In this work, we approach both problems with two contributions for improving CAM learning. First, we incorporate importance sampling based on the class-wise probability mass function induced by the CAMs to produce stochastic image-level class predictions. This results in CAMs which activate over a larger extent of objects. Second, we formulate a feature similarity loss term which aims to match the prediction contours with edges in the image. As a third contribution, we conduct experiments on the PASCAL VOC 2012 benchmark dataset to demonstrate that these modifications significantly increase the performance in terms of contour accuracy, while being comparable to current state-of-the-art methods in terms of region similarity.
arXiv commentUpdated to the version published at ICASSP2022
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Res2Net: A New Multi-scale Backbone Architecture
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- Learning random-walk label propagation for weakly-supervised semantic segmentation
- Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning