Research map / Detection and segmentation / CNN features
InfraNet: Quality-Aware RGB Guidance for Infrared Object Detection
Zichao Feng, Haodong Zhu, JingYing Yang, Linlin Yang, Yangyang Ren, Sheng Xu, Yuguang Yang, Xuhui Liu, Juan Zhang, Tian Wang, Baochang Zhang
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 IR amplification (alpha(q)) (ablation) | QualGate · LLVIP | mAP: 67.2 -> 68.8 | Improved |
| add RGB suppression (w_rgb) (ablation) | QualGate · LLVIP | mAP: 68.4 -> 68.8 | Improved |
| add learned reliability score q instead of q=1 (ablation) | InfraNet-IR · LLVIP | mAP: 67.7 -> 68.8 | Improved |
| use QualGate instead of CAGF (ablation) | InfraNet-IR · LLVIP | mAP: 66.8 -> 68.8 | Improved |
| use QualGate instead of CRLM (ablation) | InfraNet-IR · LLVIP | mAP: 66.7 -> 68.8 | Improved |
| use QualGate instead of HalluciDet pseudo-RGB guidance (ablation) | InfraNet-IR · LLVIP | mAP: 64.9 -> 68.8 | Improved |
| add learned reliability control under fog degradation level 1.0 (ablation) | InfraNet · LLVIP RGB fog | AP50/AP: 92.6/61.8 -> 97.1/67.8 | Improved |
| add learned reliability control under brightness degradation level 1.0 (ablation) | InfraNet · LLVIP RGB brightness | AP50/AP: 93.6/63.9 -> 96.5/66.4 | Improved |
| add auxiliary RGB supervision at training for IR-only deployment | YOLOv8 IR baseline · M3FD | AP50: 84.8 -> 86.2 | Improved |
| add RGB input at inference (RGB-IR) | InfraNet-IR · M3FD | AP50: 86.2 -> 89.9 | Improved |
| auxiliary weight w_aux 0.25 versus 0.0 (ablation) | InfraNet-IR · LLVIP | mAP: 68.0 -> 68.8 | Improved |
| raise auxiliary weight w_aux from 0.25 to 1.0 (ablation) | InfraNet-IR · LLVIP | mAP: 68.8 -> 68.1 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- WaveMamba — WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection (ICCV 2025) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation (ECCV 2026 · similarity 0.89)
- Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion (ECCV 2026 · similarity 0.88)
- Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection (TPAMI 2024 · similarity 0.87)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.84)
- UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation (ICLR 2025 · similarity 0.84)
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.
