Research map / Detection and segmentation / CNN features
Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning
Tianyi Zhao, Boyang Liu, Yanglei Gao, Yiming Sun, Maoxun Yuan, Xingxing Wei
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 M2D mono-modality distillation (ablation) | naive add baseline · FLIR | mAP: 43.5 -> 45.1 | Improved |
| add M2D mono-modality distillation (ablation) | naive add baseline · DroneVehicle | mAP: 66.9 -> 69.2 | Improved |
| add M2D mono-modality distillation (ablation) | naive add baseline · LLVIP | mAP: 68.2 -> 70.7 | Improved |
| add LIF fusion module (ablation) | naive add baseline · FLIR | mAP: 43.5 -> 45.0 | Improved |
| add LIF fusion module (ablation) | naive add baseline · DroneVehicle | mAP: 66.9 -> 68.5 | Improved |
| add LIF fusion module (ablation) | naive add baseline · LLVIP | mAP: 68.2 -> 69.4 | Improved |
| add LIF on top of M2D (ablation) | M2D-LIF · FLIR | mAP: 45.1 -> 46.1 | Improved |
| add LIF on top of M2D (ablation) | M2D-LIF · DroneVehicle | mAP: 69.2 -> 70.6 | Improved |
| add M2D on top of LIF (ablation) | M2D-LIF · LLVIP | mAP: 69.4 -> 70.8 | Improved |
| add L-channel supervision to learned LIF weights (ablation) | LIF · FLIR | mAP: 45.0 -> 46.1 | Improved |
| learned LIF weight instead of normalized L-channel as fusion weight (ablation) | LIF · FLIR | mAP: 44.2 -> 46.1 | Improved |
| add M2D training to IWM weighted fusion (ablation) | IWM · FLIR | mAP: 44.0 -> 44.9 | Improved |
Closest papers by meaning
- Taming Cascaded Mixture-of-Experts for Modality-missing Multi-modal Salient Object Detection (AAAI 2026 · similarity 0.90)
- CNN-Based RGB-D Salient Object Detection: Learn, Select, and Fuse (IJCV 2021 · similarity 0.89)
- MLLM Makes Strong Backbone for Multi-Modal Object Detection (NeurIPS 2026 · similarity 0.88)
- CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection (CVPR 2026 · similarity 0.88)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.87)
- E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection (NeurIPS 2024 · similarity 0.86)
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.
