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

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

2505.00938 2025-05-02 이 페이지의 평가 6건

mAP: 59.0

Detecting Twenty-thousand Classes using Image-level Supervision

2201.02605 2022-01-07 이 페이지의 평가 6건

mAP: 0.1

Detect Everything with Few Examples

2309.12969 2023-09-22 이 페이지의 평가 4건

mAP: 40.8

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 3건

mAP: 61.5

Exploring Plain Vision Transformer Backbones for Object Detection

2203.16527 2022-03-30 이 페이지의 평가 3건

mAP: 25.6

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

2507.02798 2025-07-03 이 페이지의 평가 3건

mAP: 25.9

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

2024-05-23 이 페이지의 평가 2건

mAP: 20.4

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

2402.03094 2024-02-05 이 페이지의 평가 2건

mAP: 44.3

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

2108.09017 2021-08-20 이 페이지의 평가 1건

mAP: 12.1