paper-with-me

Few-Shot Object Detection

10개 벤치마크 · 논문 189편 · 이 태스크의 논문 보기 →

Benchmarks

MS-COCO (10-shot)

결과 198개

CAMO-FS

결과 156개

MS-COCO (30-shot)

결과 150개

LVIS v1.0 val

결과 42개

MS-COCO (1-shot)

결과 42개

LVIS v1.0 test-dev

결과 30개

ODinW-13

결과 18개

ODinW-35

결과 18개

COCO 2017

결과 6개

MS-COCO (5-shot)

결과 6개

Most implemented

Papers

Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models

2026-07-01 · Kensuke Nakamura, Byung-Woo Hong arxiv

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 Localization

Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

2026-06-22 · KunHo Heo, Seungjae Kim, Wongyu Lee, SuYeon Kim 외 arxiv

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 Detection

Proposal Refinement for Few-Shot Object Detection

2026-06-08 · Yuan Zeng, Bin Song, Jie Guo, Yuwen Chen arxiv

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 Detection

Decoupled Prototype Matching with Vision Foundation Models for Few-Shot Industrial Object Detection

2026-04-29 · Hari Prasanth S. M., Nilusha Jayawickrama, Risto Ojala arxiv

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 Estimation

DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

2026-03-24 · Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov, Shruti Jain 외 arxiv

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 Grounding

FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion

2026-02-03 · Chen-Bin Feng, Youyang Sha, Longfei Liu, Yongjun Yu 외 arxiv

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

전체 189편 보기 →