Semantically-Guided Disentangled Representation for Robust Gait Recognition

Gait is an important biometric that can recognize people at a distance. Recently, Disentangled Representation Learning (DRL) has been introduced for distinguishing identity-irrelevant covariate features from identity features for better recognition performance. However, such a simple gait energy image (GEI) pairing operation inevitably brings in over-disentanglement effects that degrade the performance. To address this issue, we proposed a covariate feature control gate module that compensates for the discriminative feature loss by using additional semantic labels. Furthermore, a shared attention module, which allows the identity and covariate part to pay attention to different spatial regions, is also proposed for better spatial disentanglement. Experimental results show that our method outperforms the state-of-the-art and well-explain the mechanism of how the improvement is achieved. The code is available at https://github.com/ctrasd/GA-ICDNet.