# Spectral Aware Softmax for Visible-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2302.01512 · HTML: https://mlsanity.com/paper/2302.01512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 21 of 21)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2004.08787/) (2020)
- [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020)
- [Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/1912.01230/) (2019)
- [Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification](https://mlsanity.com/paper/2104.02862/) (2021)
- [Learning Disentangled Representation for Robust Person Re-identification](https://mlsanity.com/paper/1910.12003/) (2019)
- [Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2008.02520/) (2020)

## Built on by (most cited first, 1 of 1)

- [RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification](https://mlsanity.com/paper/2411.01225/) (2024)

## Abstract (arXiv)

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.