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.

Interpreting Biomedical VLMs on High-Imbalance Out-of-Distributions: An Insight into BiomedCLIP on Radiology

Add code
Jun 17, 2025
Viaarxiv icon

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

Add code
Jun 06, 2025
Viaarxiv icon

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment

Add code
Jun 11, 2025
Viaarxiv icon

Locality-Aware Zero-Shot Human-Object Interaction Detection

Add code
May 26, 2025
Viaarxiv icon

Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection

Add code
Jun 06, 2025
Viaarxiv icon

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation

Add code
May 20, 2025
Viaarxiv icon

Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models

Add code
May 27, 2025
Viaarxiv icon

Joint User Association and Beamforming Design for ISAC Networks with Large Language Models

Add code
Jun 05, 2025
Viaarxiv icon

Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry

Add code
May 30, 2025
Viaarxiv icon

Electrolyzers-HSI: Close-Range Multi-Scene Hyperspectral Imaging Benchmark Dataset

Add code
May 26, 2025
Viaarxiv icon