Few-Shot Object Detection

19 papers with code • 4 benchmarks • 3 datasets

Target: To detect objects of novel categories with just a few training samples.

Greatest papers with code

Frustratingly Simple Few-Shot Object Detection

ucbdrive/few-shot-object-detection ICML 2020

Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.

Few-Shot Object Detection Meta-Learning

Few-shot Object Detection via Feature Reweighting

bingykang/Fewshot_Detection ICCV 2019

The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.

Few-Shot Learning Few-Shot Object Detection +1

Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

fanq15/Few-Shot-Object-Detection-Dataset CVPR 2020

To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations.

Ranked #5 on Few-Shot Object Detection on MS-COCO (10-shot) (using extra training data)

Few-Shot Object Detection

One-Shot Instance Segmentation

bethgelab/siamese-mask-rcnn 28 Nov 2018

We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult.

Few-Shot Object Detection One-Shot Instance Segmentation +2

Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning

yanxp/MetaR-CNN ICCV 2019

Resembling the rapid learning capability of human, low-shot learning empowers vision systems to understand new concepts by training with few samples.

Few-Shot Object Detection Meta-Learning +1

RepMet: Representative-based metric learning for classification and one-shot object detection

jshtok/RepMet 12 Jun 2018

Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples.

Classification Few-Shot Object Detection +4

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

jiaxi-wu/MPSR ECCV 2020

Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.

Few-Shot Object Detection

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

MegviiDetection/FSCE 10 Mar 2021

We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.

Few-Shot Learning Few-Shot Object Detection +1

LSTD: A Low-Shot Transfer Detector for Object Detection

Cassie94/LSTD 5 Mar 2018

Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images.

Few-Shot Object Detection Transfer Learning