# Beyond Symmetric Fusion: Exploiting Task-Dependent Modality Strengths for RGB-Event Small Object Detection

arXiv: https://arxiv.org/abs/2608.01302 · HTML: https://mlsanity.com/paper/2608.01302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Recurrent Vision Transformers for Object Detection with Event Cameras](https://mlsanity.com/paper/2212.05598/) (2022)
- [PMR: Prototypical Modal Rebalance for Multimodal Learning](https://mlsanity.com/paper/2211.07089/) (2022)
- [Cross-Modality Fusion Transformer for Multispectral Object Detection](https://mlsanity.com/paper/2111.00273/) (2021)
- [ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection](https://mlsanity.com/paper/2308.07504/) (2023)
- [MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance](https://mlsanity.com/paper/2405.17730/) (2024)
- [SODFormer: Streaming Object Detection with Transformer Using Events and Frames](https://mlsanity.com/paper/2308.04047/) (2023)
- [Improving Multimodal Learning via Imbalanced Learning](https://mlsanity.com/paper/2507.10203/) (2025)
- [FRED: The Florence RGB-Event Drone Dataset](https://mlsanity.com/paper/2506.05163/) (2025)
- [Drone Detection with Event Cameras](https://mlsanity.com/paper/2508.04564/) (2025)
- [PEPR: Privileged Event-based Predictive Regularization for Domain Generalization](https://mlsanity.com/paper/2602.04583/) (2026)
- [SparseVoxelDet: Fully Sparse Voxel Networks for Efficient Event-Based Drone Detection](https://mlsanity.com/paper/2603.21638/) (2026)

## Abstract (arXiv)

State-of-the-art RGB-Event detectors improve the detection of small, fast-moving objects by combining complementary features from RGB and Event data, yet they typically fuse the two modalities into a unified representation for both localization and classification. Such a task-symmetric design is inconsistent with the intuition that the two modalities should play different roles according to their task-specific strengths. To examine this issue, we conduct a modality-specific evaluation and find that the relative advantage of the two modalities reverses across tasks: Event data are substantially more effective for class-agnostic localization, whereas RGB data provide stronger category evidence within localized target regions. Motivated by this task-dependent asymmetry, we propose an Asymmetric Event-RGB Object Detection Transformer (AERODet). During class-agnostic localization, Scale-wise Uncertainty-aware Reliability Estimation (SURE) calculates the relative reliability of the two modalities from their objectness response heatmaps and accordingly calibrates their contributions when the decoder aggregates multimodal features. Once the candidate boxes are obtained, Task-Decoupled Semantic Refinement (TDSR) decouples classification from localization and uses RGB RoI features for fine-grained classification. Extensive experiments on FRED and NeRDD demonstrate that AERODet achieves state-of-the-art performance. In particular, it surpasses the strongest RGB-Event baseline by 10.7 mAP points on the FRED challenging split.