Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Few-Shot Object Detection

3260 papers • 126 benchmarks • 313 datasets

Few-Shot Object Detection is a computer vision task that involves detecting objects in images with limited training data. The goal is to train a model on a few examples of each object class and then use the model to detect objects in new images.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in few-shot-object-detection

Trend

Dataset

Best Model

Actions

MS-COCO (10-shot)

MS-COCO (10-shot)

MS-COCO (30-shot)

MS-COCO (30-shot)

MS-COCO (1-shot)

Libraries

i

Use these libraries to find few-shot-object-detection models and implementations

3 papers 15

Datasets

LVIS

FSOD

ELEVATER

BankNote-Net

VizWiz-FewShot

Subtasks

No subtasks available.

Most implemented papers

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

Jianfeng Gao, Houdong Hu, Zicheng Liu, Jianwei Yang, Pengchuan Zhang, Haotian Liu, Liunian Harold Li, J. Aneja, Ping Jin, Yong Jae Lee•Mon Apr 18 2022

This work builds ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating (pre-trained) language-AUgmented visual models.

178

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

MS-COCO (1-shot)

ODinW-35

ODinW-35

ODinW-13

ODinW-13

LVIS v1.0 val

LVIS v1.0 val

COCO 2017

COCO 2017

LVIS v1.0 test-dev

LVIS v1.0 test-dev

2 papers 1,930

Ze-Yang/Context-Transformer

2 papers 102

lexisnexis-risk-open-source/ledetec…

2 papers 29

0

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

Yunhong Wang, Di Huang, Jiaxi Wu, Songtao Liu•Fri Jul 17 2020

This work proposes a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD, which generates multi-scale positive samples as object pyramids and refines the prediction at various scales.

339 0

One-Shot Instance Segmentation

M. Bethge, Claudio Michaelis, Alexander S. Ecker, Ivan Ustyuzhaninov•Tue Nov 27 2018

Siamese Mask R-CNN is extended by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category.

96 0

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

Yu-Wing Tai, Qi Fan, W. Zhuo•Mon Aug 05 2019

A novel few-shot object detection network that aims at detecting objects of unseen categories with only a few annotated examples, which exploits the similarity between the few shot support set and query set to detect novel objects while suppressing false detection in the background.

606 0

Few-Shot Object Detection via Feature Reweighting

Jiashi Feng, Bingyi Kang, Trevor Darrell, Zhuang Liu, F. Yu, Xin Wang•Tue Dec 04 2018

This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture.

808 0

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan•Tue Mar 09 2021

This work presents 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.

496 0

Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection

Qixiang Ye, Bohao Li, Rongrong Ji, Boyu Yang, Chang Liu, Feng Liu•Sun Mar 07 2021

A class margin equilibrium (CME) approach, with the aim to optimize both feature space partition and novel class reconstruction in a systematic way, achieving state-of-the-art performance.

176 0

Frustratingly Simple Few-Shot Object Detection

Trevor Darrell, Joseph E. Gonzalez, F. Yu, Thomas E. Huang•Sun Mar 15 2020

This work finds that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task, and establishes a new state of the art on the revised benchmarks.

687 0

Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

V. Lepetit, Renaud Marlet, Yang Xiao•Wed Jul 22 2020

This paper tackles the problems of few-shot object detection and few- shot viewpoint estimation, and introduces a simple category-agnostic viewpoint estimation method that outperforms state-of-the-art methods by a large margin on a range of datasets.

388 0

Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

Fang Wan, Qixiang Ye, Feng Liu, Zhiliang Peng, Xiaosong Zhang, Zonghao Guo, Xian-Wei Ji•Wed May 18 2022

This study proposes to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is "fully pre-trained" so that detectors’ generalization capacity is maximized.

28 0

Adding a benchmark result helps the community track progress.

Few-Shot Object Detection | State-of-the-Art