Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification
This work addresses fine-grained visual categorization and object re-identification for computer vision applications, presenting an incremental improvement over existing self-attention methods.
The paper tackles the problem of recognizing fine-grained objects like bird species or person identities by proposing a dual cross-attention learning algorithm to enhance self-attention mechanisms, resulting in performance improvements such as surpassing DeiT-Tiny and ViT-Base by 2.8% and 2.4% mAP on MSMT17.
Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention modules to better learn subtle feature embeddings for recognizing fine-grained objects, e.g., different bird species or person identities. To this end, we propose a dual cross-attention learning (DCAL) algorithm to coordinate with self-attention learning. First, we propose global-local cross-attention (GLCA) to enhance the interactions between global images and local high-response regions, which can help reinforce the spatial-wise discriminative clues for recognition. Second, we propose pair-wise cross-attention (PWCA) to establish the interactions between image pairs. PWCA can regularize the attention learning of an image by treating another image as distractor and will be removed during inference. We observe that DCAL can reduce misleading attentions and diffuse the attention response to discover more complementary parts for recognition. We conduct extensive evaluations on fine-grained visual categorization and object re-identification. Experiments demonstrate that DCAL performs on par with state-of-the-art methods and consistently improves multiple self-attention baselines, e.g., surpassing DeiT-Tiny and ViT-Base by 2.8% and 2.4% mAP on MSMT17, respectively.