SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 179 papers

TitleStatusHype
No time to train! Training-Free Reference-Based Instance SegmentationCode3
Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationCode1
CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature ConfusionCode1
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and ResultsCode2
Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object DetectionCode2
Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object DetectionCode2
Multimodal Reference Visual Grounding—0
Context in object detection: a systematic literature review—0
Exploring Few-Shot Object Detection on Blood Smear Images: A Case Study of Leukocytes and Schistocytes—0
Visual-RFT: Visual Reinforcement Fine-TuningCode7
Show:102550
← PrevPage 1 of 18Next →
All datasetsMS-COCO (10-shot)CAMO-FSMS-COCO (30-shot)LVIS v1.0 valMS-COCO (1-shot)LVIS v1.0 test-devODinW-13ODinW-35COCO 2017MS-COCO (5-shot)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UniFSAP18.2—Unverified