Research map / Label-efficient and robust learning / Recognition and long-tail
Channel Augmented Joint Learning for Visible-Infrared Recognition
Mang Ye, Weijian Ruan, Bo Du, Mike Zheng Shou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add random channel exchangeable augmentation (ablation) | AGW baseline · SYSU-MM01 all search | Rank-1: 49.87 -> 54.29 | Improved |
| add channel-level random erasing to channel augmentation (ablation) | AGW + CA · SYSU-MM01 all search | Rank-1: 54.29 -> 65.28 | Improved |
| add random grayscale augmentation (ablation) | AGW + CA + CRE · SYSU-MM01 all search | Rank-1: 65.28 -> 65.91 | Improved |
| add random horizontal flip (ablation) | AGW + CA + CRE + GA · SYSU-MM01 all search | Rank-1: 65.91 -> 67.02 | Improved |
| add enhanced squared difference to channel-mixed learning (ablation) | M · SYSU-MM01 all search | Rank-1: 67.02 -> 69.16 | Improved |
| add enhanced squared difference to joint learning (ablation) | J · SYSU-MM01 all search | Rank-1: 67.68 -> 69.88 | Improved |
| add channel-augmented joint learning (with squared difference) (ablation) | M · SYSU-MM01 all search | Rank-1: 69.16 -> 69.88 | Improved |
| add channel-augmented joint learning (ablation) | AGW + augmentations · SYSU-MM01 all search | Rank-1: 67.02 -> 69.88 | Improved |
| use squared difference instead of hard triplet mining (ablation) | J · SYSU-MM01 all search | Rank-1: 66.41 -> 69.88 | Improved |
| add channel augmentation and ours to DDAG | DDAG · SYSU-MM01 all search | Rank-1: 54.75 -> 62.51 | Improved |
| add channel augmentation and random erasing to LightCNN-29 | LightCNN-29 · Oulu-CASIA NIR-VIS | VR@FAR=0.1%: 87.0 -> 91.7 | Improved |
| add channel augmentation and random erasing to LightCNN-29 | LightCNN-29 · BUAA-VisNir | Rank-1: 98.0 -> 98.3 | Improved |
Closest papers by meaning
- Channel Augmentation for Visible-Infrared Re-Identification (TPAMI 2023 · similarity 0.94)
- Augmented and Softened Matching for Unsupervised Visible-Infrared Person Re-Identification (ICCV 2025 · similarity 0.86)
- FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection (AAAI 2025 · similarity 0.83)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.83)
- IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning (AAAI 2024 · similarity 0.83)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
