Few-Shot Object Detection

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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 179 papers

Title	Date	Tasks	Status	Hype
No time to train! Training-Free Reference-Based Instance Segmentation	Jul 3, 2025	Cross-Domain Few-Shot Object DetectionFew-Shot Object Detection	CodeCode Available	3
Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation	May 20, 2025	Few-Shot Object DetectionInstance Segmentation	CodeCode Available	1
CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion	May 2, 2025	Cross-Domain Few-ShotCross-Domain Few-Shot Object Detection	CodeCode Available	1
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results	Apr 14, 2025	Cross-Domain Few-ShotCross-Domain Few-Shot Object Detection	CodeCode Available	2
Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection	Apr 9, 2025	Contrastive Learningcounterfactual	CodeCode Available	2
Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection	Apr 6, 2025	Cross-Domain Few-ShotCross-Domain Few-Shot Object Detection	CodeCode Available	2
Multimodal Reference Visual Grounding	Apr 2, 2025	Few-Shot Object DetectionVisual Grounding	—Unverified	0
Context in object detection: a systematic literature review	Mar 29, 2025	Few-Shot Object DetectionObject	—Unverified	0
Exploring Few-Shot Object Detection on Blood Smear Images: A Case Study of Leukocytes and Schistocytes	Mar 21, 2025	Few-Shot Object Detectionobject-detection	—Unverified	0
Visual-RFT: Visual Reinforcement Fine-Tuning	Mar 3, 2025	Few-Shot Object DetectionFine-Grained Image Classification	CodeCode Available	7

Show:10 25 50

← PrevPage 1 of 18Next →

All datasets MS-COCO (10-shot)CAMO-FS MS-COCO (30-shot)LVIS v1.0 val MS-COCO (1-shot)LVIS v1.0 test-dev ODinW-13 ODinW-35 COCO 2017 MS-COCO (5-shot)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	best_single_model_val	AP	47.55	—	Unverified
2	htc	AP	39.05	—	Unverified
3	Organizer Provided Baseline	AP	27.26	—	Unverified
4	null	AP	25.8	—	Unverified
5	Forest R-CNN	AP	23.2	—	Unverified
6	person	AP	21.82	—	Unverified
7	test balloon 6	AP	16.62	—	Unverified