# Towards Robust Cross-Dataset Object Detection Generalization under Domain Specificity

arXiv: https://arxiv.org/abs/2601.09497 · HTML: https://mlsanity.com/paper/2601.09497/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data](https://mlsanity.com/paper/2012.05400/) (2020)
- [Spatial Attention Pyramid Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2003.12979/) (2020)
- [Curriculum Self-Paced Learning for Cross-Domain Object Detection](https://mlsanity.com/paper/1911.06849/) (2019)
- [Decoupled Adaptation for Cross-Domain Object Detection](https://mlsanity.com/paper/2110.02578/) (2021)
- [COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts](https://mlsanity.com/paper/2307.12730/) (2023)
- [Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection](https://mlsanity.com/paper/2304.09446/) (2023)
- [Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling](https://mlsanity.com/paper/2307.07944/) (2023)
- [Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation](https://mlsanity.com/paper/1806.09755/) (2018)
- [SimROD: A Simple Adaptation Method for Robust Object Detection](https://mlsanity.com/paper/2107.13389/) (2021)
- [Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning](https://mlsanity.com/paper/1911.07158/) (2019)
- [Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detection](https://mlsanity.com/paper/2407.04061/) (2024)
- [Embodied Domain Adaptation for Object Detection](https://mlsanity.com/paper/2506.21860/) (2025)
- [PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers](https://mlsanity.com/paper/2307.00313/) (2023)
- [Feature Based Methods in Domain Adaptation for Object Detection: A Review Paper](https://mlsanity.com/paper/2412.17325/) (2024)
- [Visually Similar Pair Alignment for Robust Cross-Domain Object Detection](https://mlsanity.com/paper/2504.06607/) (2025)

## Abstract (arXiv)

Object detectors often perform well in-distribution, yet degrade sharply on a different benchmark. We study cross-dataset object detection (CD-OD) through a lens of setting specificity. We group benchmarks into setting-agnostic datasets with diverse everyday scenes and setting-specific datasets tied to a narrow environment, and evaluate a standard detector family across all train--test pairs. This reveals a clear structure in CD-OD: transfer within the same setting type is relatively stable, while transfer across setting types drops substantially and is often asymmetric. The most severe breakdowns occur when transferring from specific sources to agnostic targets, and persist after open-label alignment, indicating that domain shift dominates in the hardest regimes. To disentangle domain shift from label mismatch, we compare closed-label transfer with an open-label protocol that maps predicted classes to the nearest target label using CLIP similarity. Open-label evaluation yields consistent but bounded gains, and many corrected cases correspond to semantic near-misses supported by the image evidence. Overall, we provide a principled characterization of CD-OD under setting specificity and practical guidance for evaluating detectors under distribution shift. Code will be released at href[https://github.com/Ritabrata04/cdod-icpr.githttps://github.com/Ritabrata04/cdod-icpr.