Liqing Huang

Yunpeng Gong, Liqing Huang, Lifei Chen

The main challenges of ReID is the intra-class variations caused by color deviation under different camera conditions. Simultaneously, we find that most of the existing adversarial metric attacks are realized by interfering with the color characteristics of the sample. Based on this observation, we first propose a local transformation attack (LTA) based on color variation. It uses more obvious color variation to randomly disturb the color of the retrieved image, rather than adding random noise. Experiments show that the performance of the proposed LTA method is better than the advanced attack methods. Furthermore, considering that the contour feature is the main factor of the robustness of adversarial training, and the color feature will directly affect the success rate of attack. Therefore, we further propose joint adversarial defense (JAD) method, which include proactive defense and passive defense. Proactive defense fuse multi-modality images to enhance the contour feature and color feature, and considers local homomorphic transformation to solve the over-fitting problem. Passive defense exploits the invariance of contour feature during image scaling to mitigate the adversarial disturbance on contour feature. Finally, a series of experimental results show that the proposed joint adversarial defense method is more competitive than a state-of-the-art methods.

Yunpeng Gong, Liqing Huang, Lifei Chen

One of the challenges of computer vision is that it needs to adapt to color deviations in changeable environments. Therefore, minimizing the adverse effects of color deviation on the prediction is one of the main goals of vision task. Current solutions focus on using generative models to augment training data to enhance the invariance of input variation. However, such methods often introduce new noise, which limits the gain from generated data. To this end, this paper proposes a strategy eliminate deviation with deviation, which is named Random Color Dropout (RCD). Our hypothesis is that if there are color deviation between the query image and the gallery image, the retrieval results of some examples will be better after ignoring the color information. Specifically, this strategy balances the weights between color features and color-independent features in the neural network by dropouting partial color information in the training data, so as to overcome the effect of color devitaion. The proposed RCD can be combined with various existing ReID models without changing the learning strategy, and can be applied to other computer vision fields, such as object detection. Experiments on several ReID baselines and three common large-scale datasets such as Market1501, DukeMTMC, and MSMT17 have verified the effectiveness of this method. Experiments on Cross-domain tests have shown that this strategy is significant eliminating the domain gap. Furthermore, in order to understand the working mechanism of RCD, we analyzed the effectiveness of this strategy from the perspective of classification, which reveals that it may be better to utilize many instead of all of color information in visual tasks with strong domain variations.