Few-Shot Object Detection
10개 벤치마크 · 논문 189편 · 이 태스크의 논문 보기 →
Benchmarks
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)
Most implemented
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
Frustratingly Simple Few-Shot Object Detection
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
Few-shot Object Detection via Feature Reweighting
Papers
Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models
Personalized object localization (POL) localizes an object instance in a query image based on a few reference images with bounding-box annotations and a target object label. The pioneering method, IPLoc, solves this task…
Few-Shot Object DetectionObject LocalizationRethinking Prototype-based Similarity Learning for Few-Shot Object Detection
Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent prototype-based similarity learning approaches enable training-free adapta…
Few-Shot Object DetectionProposal Refinement for Few-Shot Object Detection
Few-shot object detection has gained widely attention in recent years. Some excellent algorithms have been proposed to handle this task. However, most of these algorithms rely on the performance of few-shot classificatio…
Few-Shot Object DetectionDecoupled Prototype Matching with Vision Foundation Models for Few-Shot Industrial Object Detection
Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial scenarios where the inventory of objects changes frequently. This w…
Few-Shot Object Detection2D Object DetectionPose EstimationDetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribu…
Few-Shot Object DetectionVisual GroundingFSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
In this paper, we present FSOD-VFM: Few-Shot Object Detectors with Vision Foundation Models, a framework that leverages vision foundation models to tackle the challenge of few-shot object detection. FSOD-VFM integrates t…
Few-Shot Object Detection