# Few-Shot Object Detection via Knowledge Transfer

arXiv: https://arxiv.org/abs/2008.12496 · HTML: https://mlsanity.com/paper/2008.12496/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection](https://mlsanity.com/paper/2105.14891/) (2021)
- [HTNet: Anchor-free Temporal Action Localization with Hierarchical Transformers](https://mlsanity.com/paper/2207.09662/) (2022)
- [Experience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images](https://mlsanity.com/paper/2109.13027/) (2021)
- [TIDE: Test Time Few Shot Object Detection](https://mlsanity.com/paper/2311.18358/) (2023)
- [SnapCap: Efficient Snapshot Compressive Video Captioning](https://mlsanity.com/paper/2401.04903/) (2024)
- [GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints](https://mlsanity.com/paper/2108.06890/) (2021)
- [Few-Shot Batch Incremental Road Object Detection via Detector Fusion](https://mlsanity.com/paper/2108.08048/) (2021)
- [A Unified Framework for Attention-Based Few-Shot Object Detection](https://mlsanity.com/paper/2201.02052/) (2022)
- [A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images](https://mlsanity.com/paper/2210.13923/) (2022)
- [Few-Shot Object Detection with Proposal Balance Refinement](https://mlsanity.com/paper/2204.10527/) (2022)

## Abstract (arXiv)

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize. It exposes the practical weakness of the object detectors. On the other hand, human can easily master new reasoning rules with only a few demonstrations using previously learned knowledge. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples. Central to our method is prototypical knowledge transfer with an attached meta-learner. The meta-learner takes support set images that include the few examples of the novel categories and base categories, and predicts prototypes that represent each category as a vector. Then, the prototypes reweight each RoI (Region-of-Interest) feature vector from a query image to remodels R-CNN predictor heads. To facilitate the remodeling process, we predict the prototypes under a graph structure, which propagates information of the correlated base categories to the novel categories with explicit guidance of prior knowledge that represents correlations among categories. Extensive experiments on the PASCAL VOC dataset verifies the effectiveness of the proposed method.