Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing methods still follow the softmax loss training paradigm, which is widely used in single-modality classification tasks. The softmax loss lacks an explicit penalty for the apparent modality gap, which adversely limits the performance upper bound of the VI-ReID task. In this paper, we propose the spectral-aware softmax (SA-Softmax) loss, which can fully explore the embedding space with the modality information and has clear interpretability. Specifically, SA-Softmax loss utilizes an asynchronous optimization strategy based on the modality prototype instead of the synchronous optimization based on the identity prototype in the original softmax loss. To encourage a high overlapping between two modalities, SA-Softmax optimizes each sample by the prototype from another spectrum. Based on the observation and analysis of SA-Softmax, we modify the SA-Softmax with the Feature Mask and Absolute-Similarity Term to alleviate the ambiguous optimization during model training. Extensive experimental evaluations conducted on RegDB and SYSU-MM01 demonstrate the superior performance of the SA-Softmax over the state-of-the-art methods in such a cross-modality condition.
翻译:可见红外线人重新定位(VI-REID)的目的是将特定的行人图像与不同模式相匹配。虽然存在额外模式差异,但现有方法仍然遵循软体损失培训模式,这种模式在单一模式分类任务中广泛使用。软体损失对模式上明显差距缺乏明确的处罚,这种差距对VI-REID任务的性能上限有不利影响。在本文件中,我们提议光谱软体形(SA-Softmax)损失(SA-Softmax)损失,这种损失可以充分探索与模式信息嵌入的空间,并具有清晰的可解释性。具体地说,SA-Softmax损失使用基于模式原型的无同步损失培训模式而不是基于原软体损失身份原型的同步优化的无同步优化战略。为了鼓励两种模式之间的高度重叠,SA-Softmax将每个样本从另一个频谱上优化。根据对SA-Softmax损失的观察和分析,我们用Faturat 面具和绝对-Simal-Simax 损失利用模式优化战略,以缓解S-S-SDMAS-SDB的测试模型测试模型,以减缓性测试性测试性测试性测试方法进行。