Research map / Detection and segmentation / CNN features
Target-Aware Dual Adversarial Learning and a Multi-Scenario Multi-Modality Benchmark To Fuse Infrared and Visible for Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use TarDAL fusion instead of DenseFuse fusion | YOLOv5 on Multispectral · Multispectral | mAP@.5: 0.608 -> 0.613 | Helped |
| use TarDAL fusion instead of GANMcC fusion | YOLOv5 on M^3FD · M^3FD | mAP@.5: 0.797 -> 0.807 | Helped |
| add the target discriminator D_T (ablation) | TarDAL · M^3FD | mAP@.5: 0.719 -> 0.807 | Helped |
| add the detail discriminator D_D (ablation) | TarDAL · M^3FD | mAP@.5: 0.807 -> 0.781 | Hurt |
| add both target and detail discriminators (ablation) | TarDAL · TNO | MI: 2.506 -> 2.766 | Helped |
| use cooperative training instead of direct training (ablation) | TarDAL on M^3FD · M^3FD | mAP@.5: 0.807 -> 0.811 | Helped |
| use cooperative training instead of detection-loss-only training (ablation) | TarDAL on M^3FD · M^3FD | mAP@.5: 0.809 -> 0.811 | Helped |
| use cooperative training instead of detection-loss-only training (ablation) | TarDAL on Multispectral · Multispectral | mAP@.5: 0.615 -> 0.624 | Helped |
| remove the saliency degree weight (SDW) pixel loss (ablation) | TarDAL · Fusion visual quality | salient pixel contrast | Hurt |
| remove the target mask m from discriminator training (ablation) | TarDAL · Fusion visual quality | detail preservation | Hurt |
Closest papers by meaning
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.86)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 2024 · similarity 0.85)
- Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion (ICLR 2025 · similarity 0.85)
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.84)
- Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection (AAAI 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.