# Rethinking Multi-Modal Object Detection from the Perspective of Mono-Modality Feature Learning

arXiv: https://arxiv.org/abs/2503.11780 · HTML: https://mlsanity.com/paper/2503.11780/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2025.

## Built on by (most cited first, 11 of 11)

- [RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios](https://mlsanity.com/paper/2512.24561/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detection](https://mlsanity.com/paper/2511.15433/) (2025)
- [Breaking Self-Attention Failure: Rethinking Query Initialization for Infrared Small Target Detection](https://mlsanity.com/paper/2601.02837/) (2026)
- [UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detection](https://mlsanity.com/paper/2603.17492/) (2026)
- [Tri-Modal Fusion Transformers for UAV-based Object Detection](https://mlsanity.com/paper/2604.16630/) (2026)
- [ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT Object Detection](https://mlsanity.com/paper/2608.11595/) (2026)
- [EGM-Det: Entropy-Guided Multimodal Adaptive Fusion for UAV RGB-IR Object Detection](https://mlsanity.com/paper/2608.11685/) (2026)
- [A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration](https://mlsanity.com/paper/2608.21099/) (2026)
- [Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery](https://mlsanity.com/paper/2609.18124/) (2026)
- [FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detection](https://mlsanity.com/paper/2609.29125/) (2026)

## Abstract (arXiv)

Multi-Modal Object Detection (MMOD), due to its stronger adaptability to various complex environments, has been widely applied in various applications. Extensive research is dedicated to the RGB-IR object detection, primarily focusing on how to integrate complementary features from RGB-IR modalities. However, they neglect the mono-modality insufficient learning problem, which arises from decreased feature extraction capability in multi-modal joint learning. This leads to a prevalent but unreasonable phenomenontextemdash Fusion Degradation, which hinders the performance improvement of the MMOD model. Motivated by this, in this paper, we introduce linear probing evaluation to the multi-modal detectors and rethink the multi-modal object detection task from the mono-modality learning perspective. Therefore, we construct a novel framework called M2D-LIF, which consists of the Mono-Modality Distillation (M2D) method and the Local Illumination-aware Fusion (LIF) module. The M2D-LIF framework facilitates the sufficient learning of mono-modality during multi-modal joint training and explores a lightweight yet effective feature fusion manner to achieve superior object detection performance. Extensive experiments conducted on three MMOD datasets demonstrate that our M2D-LIF effectively mitigates the Fusion Degradation phenomenon and outperforms the previous SOTA detectors. The codes are available at https://github.com/Zhao-Tian-yi/M2D-LIF.