Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

By Yongming Rao, Guangyi Chen, Jiwen Lu, Jie Zhou. IEEE International Conference on Computer Vision, 2021

353 citations recorded by the source corpus.

Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. Specifically, we analyze the effect of the learned visual attention on network prediction through counterfactual intervention and maximize the effect to encourage the network to learn more useful attention for fine-grained image recognition. Empirically, we evaluate our method on a wide range of fine-grained recognition tasks where attention plays a crucial role, including fine-grained image categorization, person re-identification, and vehicle re-identification. The consistent improvement on all benchmarks demonstrates the effectiveness of our method. 1

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0f64bf963ab8c5fe341c4cb9679d18e4d57917ec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Li Sun
  2. Siyuan Li
  3. Qingli Li

In Computer Vision and Pattern Recognition

  1. Li Sun
  2. Siyuan Li
  3. Qingli Li

Citations in the corpus