# Context-Transformer: Tackling Object Confusion for Few-Shot Detection

arXiv: https://arxiv.org/abs/2003.07304 · HTML: https://mlsanity.com/paper/2003.07304/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 27 of 27)

- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (2021)
- [Label, Verify, Correct: A Simple Few Shot Object Detection Method](https://mlsanity.com/paper/2112.05749/) (2021)
- [Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2306.14451/) (2023)
- [Few-Shot Object Detection via Association and DIscrimination](https://mlsanity.com/paper/2111.11656/) (2021)
- [Multi-View Correlation Distillation for Incremental Object Detection](https://mlsanity.com/paper/2107.01787/) (2021)
- [ShadowFormer: Global Context Helps Image Shadow Removal](https://mlsanity.com/paper/2302.01650/) (2023)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Goldilocks: Just-Right Tuning of BERT for Technology-Assisted Review](https://mlsanity.com/paper/2105.01044/) (2021)
- [Efficient Few-Shot Object Detection via Knowledge Inheritance](https://mlsanity.com/paper/2203.12224/) (2022)
- [Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection](https://mlsanity.com/paper/2211.14782/) (2022)
- [EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer](https://mlsanity.com/paper/2109.04235/) (2021)
- [Few-Shot Object Detection: Research Advances and Challenges](https://mlsanity.com/paper/2404.04799/) (2024)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [Few-Shot Video Object Detection](https://mlsanity.com/paper/2104.14805/) (2021)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [tSF: Transformer-based Semantic Filter for Few-Shot Learning](https://mlsanity.com/paper/2211.00868/) (2022)
- [When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework](https://mlsanity.com/paper/2201.06781/) (2022)
- [Context in object detection: a systematic literature review](https://mlsanity.com/paper/2503.23249/) (2025)
- [TIDE: Test Time Few Shot Object Detection](https://mlsanity.com/paper/2311.18358/) (2023)
- [Few-Shot Object Detection with Sparse Context Transformers](https://mlsanity.com/paper/2402.09315/) (2024)
- [Data-Efficient and Robust Task Selection for Meta-Learning](https://mlsanity.com/paper/2405.07083/) (2024)

## Abstract (arXiv)

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches.