# COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection

arXiv: https://arxiv.org/abs/2508.09533 · HTML: https://mlsanity.com/paper/2508.09533/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Cross-Modality Fusion Transformer for Multispectral Object Detection](https://mlsanity.com/paper/2111.00273/) (2021)
- [Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems](https://mlsanity.com/paper/2008.03043/) (2020)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection](https://mlsanity.com/paper/2306.16175/) (2023)
- [RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2208.08738/) (2022)
- [Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection](https://mlsanity.com/paper/2209.13801/) (2022)
- [HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection](https://mlsanity.com/paper/2206.15157/) (2022)
- [DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion](https://mlsanity.com/paper/2403.00326/) (2024)
- [Weakly Aligned Feature Fusion for Multimodal Object Detection](https://mlsanity.com/paper/2204.09848/) (2022)
- [MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking](https://mlsanity.com/paper/2408.07889/) (2024)
- [Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection](https://mlsanity.com/paper/2403.01300/) (2024)
- [Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion](https://mlsanity.com/paper/2409.09808/) (2024)

## Built on by (most cited first, 2 of 2)

- [SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection](https://mlsanity.com/paper/2511.06298/) (2025)
- [A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration](https://mlsanity.com/paper/2608.21099/) (2026)

## Abstract (arXiv)

Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and thermal modalities effectively. We propose COXNet, a novel framework for RGBT tiny object detection, addressing these issues through three core innovations: i) the Cross-Layer Fusion Module, fusing high-level visible and low-level thermal features for enhanced semantic and spatial accuracy; ii) the Dynamic Alignment and Scale Refinement module, correcting cross-modal spatial misalignments and preserving multi-scale features; and iii) an optimized label assignment strategy using the GeoShape Similarity Measure for better localization. COXNet achieves a 3.32% mAP50 improvement on the RGBTDronePerson dataset over state-of-the-art methods, demonstrating its effectiveness for robust detection in complex environments.