# Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining

arXiv: https://arxiv.org/abs/2604.11195 · HTML: https://mlsanity.com/paper/2604.11195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 74 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Learning Open Set Network with Discriminative Reciprocal Points](https://mlsanity.com/paper/2011.00178/) (2020)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [Higher-order organization of complex networks](https://mlsanity.com/paper/1612.08447/) (2016)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation](https://mlsanity.com/paper/2003.10275/) (2020)
- [SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.06398/) (2022)
- [On the Effectiveness of Image Rotation for Open Set Domain Adaptation](https://mlsanity.com/paper/2007.12360/) (2020)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)

## Abstract (arXiv)

Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and adapting to both base and novel categories in the target domain without target annotations. However, current AOOD methods remain limited by weak cross-domain representations, ambiguity among novel categories, and source-domain feature bias. To address these issues, we propose a category-level collaboration knowledge mining strategy that exploits both inter-class and intra-class relationships across domains. Specifically, we construct a clustering-based memory bank to encode class prototypes, auxiliary features, and intra-class disparity information, and iteratively update it via unsupervised clustering to enhance category-level knowledge representation. We further design a base-to-novel selection metric to discover source-domain features related to novel categories and use them to initialize novel-category classifiers. In addition, an adaptive feature assignment strategy transfers the learned category-level knowledge to the target domain and asynchronously updates the memory bank to alleviate source-domain bias. Extensive experiments on multiple benchmarks show that our method consistently surpasses state-of-the-art AOOD methods by 1.1-5.5 mAP.