Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation

by   Jiren Mai, et al.

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has long been suffering from fragmentary object regions led by Class Activation Map (CAM), which is incapable of generating fine-grained masks for semantic segmentation. To guide CAM to find more non-discriminating object patterns, this paper turns to an interesting working mechanism in agent learning named Complementary Learning System (CLS). CLS holds that the neocortex builds a sensation of general knowledge, while the hippocampus specially learns specific details, completing the learned patterns. Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) to explicitly drive a coarse-grained CAM to a fine-grained pseudo mask. Specifically, GSLM develops a General Learning Module (GLM) and a Specific Learning Module (SLM). The GLM is trained with image-level supervision to extract coarse and general localization representations from CAM. Based on the general knowledge in the GLM, the SLM progressively exploits the specific spatial knowledge from the localization representations, expanding the CAM in an explicit way. To this end, we propose the Seed Reactivation to help SLM reactivate non-discriminating regions by setting a boundary for activation values, which successively identifies more regions of CAM. Without extra refinement processes, our method is able to achieve breakthrough improvements for CAM of over 20.0 datasets, representing a new state-of-the-art among existing WSSS methods.


page 2

page 5

page 7

page 9

page 10


BoundaryCAM: A Boundary-based Refinement Framework for Weakly Supervised Semantic Segmentation of Medical Images

Weakly Supervised Semantic Segmentation (WSSS) with only image-level sup...

Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation

Training a Convolutional Neural Network (CNN) for semantic segmentation ...

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

Learning semantic segmentation from weakly-labeled (e.g., image tags onl...

On Symbiosis of Attribute Prediction and Semantic Segmentation

In this paper, we propose to employ semantic segmentation to improve per...

Learning Rich Representations For Structured Visual Prediction Tasks

We describe an approach to learning rich representations for images, tha...

Complementary Patch for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) based on image-level labe...

Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint

Class activation map (CAM) highlights regions of classes based on classi...

Please sign up or login with your details

Forgot password? Click here to reset