# Domain Contrast for Domain Adaptive Object Detection

arXiv: https://arxiv.org/abs/2006.14863 · HTML: https://mlsanity.com/paper/2006.14863/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation](https://mlsanity.com/paper/2110.12635/) (2021)
- [DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection](https://mlsanity.com/paper/2304.07082/) (2023)
- [Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2402.01304/) (2024)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [Multimodal Feature Fusion Network with Text Difference Enhancement for Remote Sensing Change Detection](https://mlsanity.com/paper/2509.03961/) (2025)
- [On the Robustness of Human-Object Interaction Detection against Distribution Shift](https://mlsanity.com/paper/2506.18021/) (2025)
- [Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation](https://mlsanity.com/paper/2510.22142/) (2025)

## Abstract (arXiv)

We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors. DC is deduced from the error bound minimization perspective of a transferred model, and is implemented with cross-domain contrast loss which is plug-and-play. By minimizing cross-domain contrast loss, DC guarantees the transferability of detectors while naturally alleviating the class imbalance issue in the target domain. DC can be applied at either image level or region level, consistently improving detectors' transferability and discriminability. Extensive experiments on commonly used benchmarks show that DC improves the baseline and state-of-the-art by significant margins, while demonstrating great potential for large domain divergence.