Further Improving Weakly-supervised Object Localization via Causal Knowledge Distillation

by   Feifei Shao, et al.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.


page 2

page 7

page 8

page 9

page 13


Improving Weakly-supervised Object Localization via Causal Intervention

The recent emerged weakly supervised object localization (WSOL) methods ...

Improving Weakly Supervised Sound Event Detection with Causal Intervention

Existing weakly supervised sound event detection (WSSED) work has not ex...

Causal Intervention for Weakly-Supervised Semantic Segmentation

We present a causal inference framework to improve Weakly-Supervised Sem...

Combinational Class Activation Maps for Weakly Supervised Object Localization

Weakly supervised object localization has recently attracted attention s...

Mitigating Biased Activation in Weakly-supervised Object Localization via Counterfactual Learning

In this paper, we focus on an under-explored issue of biased activation ...

Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection

Weakly supervised object detection (WSOD), which is an effective way to ...

Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

Deep regression trackers are among the fastest tracking algorithms avail...

Please sign up or login with your details

Forgot password? Click here to reset