Person Re-identification with Bias-controlled Adversarial Training
This work addresses bias issues in person re-identification, which is important for surveillance and security applications, but it appears incremental as it builds on existing adversarial training methods.
The paper tackles bias in person re-identification by proposing a Bias-controlled Adversarial framework to address pose, body part, and camera view biases, resulting in performance improvements in both full and partial views compared to state-of-the-art benchmarks.
Inspired by the effectiveness of adversarial training in the area of Generative Adversarial Networks we present a new approach for learning feature representations in person re-identification. We investigate different types of bias that typically occur in re-ID scenarios, i.e., pose, body part and camera view, and propose a general approach to address them. We introduce an adversarial strategy for controlling bias, named Bias-controlled Adversarial framework (BCA), with two complementary branches to reduce or to enhance bias-related features. The results and comparison to the state of the art on different benchmarks show that our framework is an effective strategy for person re-identification. The performance improvements are in both full and partial views of persons.