Institute of Semiconductors, Chinese Academy of Sciences, Beijing, 100083, China.
School of Physics and Electronics, Henan University, Kaifeng, 475000, China.
Neural Netw. 2024 Jan;169:532-541. doi: 10.1016/j.neunet.2023.11.003. Epub 2023 Nov 7.
A proposed method, Enhancement, integration, and Expansion, aims to activate the representation of detailed features for occluded person re-identification. Region and context are two important and complementary features, and integrating them in an occluded environment can effectively improve the robustness of the model. Firstly, a self-enhancement module is designed. Based on the constructed multi-stream architecture, rich and meaningful feature interference is introduced in the feature extraction stage to enhance the model's ability to perceive noise. Next, a collaborative integration module similar to cascading cross-attention is proposed. By studying the intrinsic interaction patterns of regional and contextual features, it adaptively fuses features across streams and enhances the diverse and complete representation of internal information. The module is not only robust to complex occlusions, but also mitigates the feature interference problem due to similar appearances or scenes. Finally, a matching expansion module that enhances feature discriminability and completeness is proposed. Providing more stable and accurate features for recognition. Compared with state-of-the-art methods on two occluded and holistic datasets, the proposed method is proved to be advanced and the effectiveness of the module is proved by extensive ablation studies.
一种被提出的方法，增强、集成和扩展，旨在激活详细特征的表示，以实现遮挡人员再识别。区域和上下文是两个重要且互补的特征，将它们集成在遮挡环境中可以有效地提高模型的鲁棒性。首先，设计了一个自我增强模块。基于构建的多流架构，在特征提取阶段引入丰富而有意义的特征干扰，以增强模型对噪声的感知能力。接下来，提出了一种类似于级联交叉注意的协作集成模块。通过研究区域和上下文特征的内在交互模式，自适应地融合跨流的特征，并增强内部信息的多样性和完整表示。该模块不仅对复杂遮挡具有鲁棒性，而且减轻了由于相似外观或场景而导致的特征干扰问题。最后，提出了一个匹配扩展模块，增强了特征的可区分性和完整性。为识别提供更稳定和准确的特征。与两个遮挡和整体数据集上的最新方法相比，所提出的方法被证明是先进的，并且通过广泛的消融研究证明了模块的有效性。
