# Few-shot Adaptive Faster R-CNN

arXiv: https://arxiv.org/abs/1903.09372 · HTML: https://mlsanity.com/paper/1903.09372/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2019.

## Built on by (most cited first, 30 of 42)

- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [PnP-DETR: Towards Efficient Visual Analysis with Transformers](https://mlsanity.com/paper/2109.07036/) (2021)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.01483/) (2021)
- [Domain Adaptive YOLO for One-Stage Cross-Domain Detection](https://mlsanity.com/paper/2106.13939/) (2021)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting](https://mlsanity.com/paper/2302.04832/) (2023)
- [RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2110.11036/) (2021)
- [Integrated Multiscale Domain Adaptive YOLO](https://mlsanity.com/paper/2202.03527/) (2022)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2109.09033/) (2021)
- [Domain Adaptive Person Search](https://mlsanity.com/paper/2207.11898/) (2022)
- [Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2303.10451/) (2023)
- [Best-Effort Adaptation](https://mlsanity.com/paper/2305.05816/) (2023)
- [Visual Textualization for Image Prompted Object Detection](https://mlsanity.com/paper/2506.23785/) (2025)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2308.15353/) (2023)
- [Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detection](https://mlsanity.com/paper/2407.04061/) (2024)
- [SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection](https://mlsanity.com/paper/2101.01260/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Learning Compositional Shape Priors for Few-Shot 3D Reconstruction](https://mlsanity.com/paper/2106.06440/) (2021)
- [Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey](https://mlsanity.com/paper/2304.06489/) (2023)
- [Few-Shot Domain Adaptive Object Detection for Microscopic Images](https://mlsanity.com/paper/2407.07633/) (2024)
- [Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2408.12708/) (2024)
- [Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2603.18541/) (2026)
- [Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.04523/) (2021)

## Abstract (arXiv)

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data is highly insufficient, making most existing domain adaptation methods ineffective. Second, object detection involves simultaneous localization and classification, further complicating the model adaptation process. Third, the model suffers from over-adaptation (similar to overfitting when training with a few data example) and instability risk that may lead to degraded detection performance in the target domain. To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples. We then propose a bi-level module to adapt the source trained detector to the target domain: 1) the split pooling based image level adaptation module uniformly extracts and aligns paired local patch features over locations, with different scale and aspect ratio; 2) the instance level adaptation module semantically aligns paired object features while avoids inter-class confusion. Meanwhile, a source model feature regularization (SMFR) is applied to stabilize the adaptation process of the two modules. Combining these contributions gives a novel few-shot adaptive Faster-RCNN framework, termed FAFRCNN, which effectively adapts to target domain with a few labeled samples. Experiments with multiple datasets show that our model achieves new state-of-the-art performance under both the interested few-shot domain adaptation(FDA) and unsupervised domain adaptation(UDA) setting.