Papers with Code · CC BY-SA 4.0

Few-Shot Object Detection

2D Object Detection › Object Detection › Few-Shot Object Detection 187 평가 기록 16 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.

논문

Detect Everything with Few Examples

2309.12969 2023-09-22 이 페이지의 평가 5건

mAP: 9.2

Detecting Twenty-thousand Classes using Image-level Supervision

2201.02605 2022-01-07 이 페이지의 평가 5건

mAP: 12.0

CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion

2505.00938 2025-05-02 이 페이지의 평가 4건

mAP: 18.1

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

2402.03094 2024-02-05 이 페이지의 평가 2건

mAP: 12.8

DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

2108.09017 2021-08-20 이 페이지의 평가 2건

mAP: 15.5

Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection

2504.04517 2025-04-06 이 페이지의 평가 2건

mAP: 26.1

Exploring Plain Vision Transformer Backbones for Object Detection

2203.16527 2022-03-30 이 페이지의 평가 2건

mAP: 15.8

Frustratingly Simple Few-Shot Object Detection

2003.06957 2020-03-16 이 페이지의 평가 2건

mAP: 14.8

Meta-RCNN: Meta Learning for Few-Shot Object Detection

2019-09-25 이 페이지의 평가 2건

mAP: 14.0

No time to train! Training-Free Reference-Based Instance Segmentation

2507.02798 2025-07-03 이 페이지의 평가 2건

mAP: 5.5

Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners

2024-05-23 이 페이지의 평가 1건

mAP: 31.1

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

2103.05950 2021-03-10 이 페이지의 평가 1건

mAP: 21.9