Runqing Zhang

Hao Zou, Runqing Zhang, Xue Zhou et al.

Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: (1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. (2) Generative Intermediate Fusion (GIF), which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The results justify the effectiveness of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA.

Runqing Zhang, Tianshu Zhu

Humans can effectively find salient regions in complex scenes. Self-attention mechanisms were introduced into Computer Vision (CV) to achieve this. Attention Augmented Convolutional Network (AANet) is a mixture of convolution and self-attention, which increases the accuracy of a typical ResNet. However, The complexity of self-attention is O(n2) in terms of computation and memory usage with respect to the number of input tokens. In this project, we propose EAANet: Efficient Attention Augmented Convolutional Networks, which incorporates efficient self-attention mechanisms in a convolution and self-attention hybrid architecture to reduce the model's memory footprint. Our best model show performance improvement over AA-Net and ResNet18. We also explore different methods to augment Convolutional Network with self-attention mechanisms and show the difficulty of training those methods compared to ResNet. Finally, we show that augmenting efficient self-attention mechanisms with ResNet scales better with input size than normal self-attention mechanisms. Therefore, our EAANet is more capable of working with high-resolution images.

Runqing Zhang, Xue Zhou

Most existing text-to-image person retrieval methods usually assume that the training image-text pairs are perfectly aligned; however, the noisy correspondence(NC) issue (i.e., incorrect or unreliable alignment) exists due to poor image quality and labeling errors. Additionally, random masking augmentation may inadvertently discard critical semantic content, introducing noisy matches between images and text descriptions. To address the above two challenges, we propose a noise label suppression method to mitigate NC and an Attention-Weighted Selective Mask (AWM) strategy to resolve the issues caused by random masking. Specifically, the Bidirectional Similarity Distribution Matching (BSDM) loss enables the model to effectively learn from positive pairs while preventing it from over-relying on them, thereby mitigating the risk of overfitting to noisy labels. In conjunction with this, Weight Adjustment Focal (WAF) loss improves the model's ability to handle hard samples. Furthermore, AWM processes raw images through an EMA version of the image encoder, selectively retaining tokens with strong semantic connections to the text, enabling better feature extraction. Extensive experiments demonstrate the effectiveness of our approach in addressing noise-related issues and improving retrieval performance.