Few-Shot Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 110
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/guangxinghan/meta-faster-r-cnn
공식 코드Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
https://github.com/hanyue1648/reft
공식 코드Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation
https://github.com/hlings/acrofod
공식 코드AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection
https://github.com/hzhupku/DCNet
공식 코드Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
https://github.com/idea-research/grounding-dino-1.5-api
공식 코드Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
https://github.com/imnotprepared/airshot
공식 코드AirShot: Efficient Few-Shot Detection for Autonomous Exploration
https://github.com/infinity7428/hANMCL
공식 코드Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning
https://github.com/jaraxxus-me/airdet
공식 코드AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
https://github.com/jaychempan/ETS
공식 코드https://github.com/jiaxi-wu/MPSR
공식 코드Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
https://github.com/jin-s13/unifs
공식 코드UniFS: Universal Few-shot Instance Perception with Point Representations
https://github.com/johnmaijer/x-few-_cd-fsod
공식 코드NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
https://github.com/juliozhao97/efftrans_fsdet
공식 코드Exploring Effective Knowledge Transfer for Few-shot Object Detection
https://github.com/leenamx/ge-fsod
공식 코드Generalization-Enhanced Few-Shot Object Detection in Remote Sensing
https://github.com/lexisnexis-risk-open-source/ledetection
공식 코드LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection
https://github.com/lexisnexis-risk-open-source/simltd
공식 코드SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
https://github.com/liewfeng/imted
공식 코드Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
https://github.com/liuweijie19980216/DRL-for-FSOD
공식 코드https://github.com/liuziyu77/visual-rft
공식 코드https://github.com/lovelyqian/CDFSOD-benchmark
공식 코드Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
https://github.com/lovelyqian/ntire2025_cdfsod
공식 코드NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
https://github.com/lyanna4869/InfRS
공식 코드InfRS: Incremental Few-Shot Object Detection in Remote Sensing Images
https://github.com/microsoft/GLIP
공식 코드https://github.com/miquel-espinosa/no-time-to-train
공식 코드No time to train! Training-Free Reference-Based Instance Segmentation
https://github.com/mlzxy/devit
공식 코드https://github.com/nvakhoa/mpad
공식 코드Multi-Perspective Data Augmentation for Few-shot Object Detection
https://github.com/phoenix-v/digeo
공식 코드DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
https://github.com/pierlj/aaf_framework
공식 코드A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images
https://github.com/prannaykaul/lvc
공식 코드Label, Verify, Correct: A Simple Few Shot Object Detection Method
https://github.com/pumpkinder/glip-cdfsod
공식 코드NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
https://github.com/rsCPSyEu/ovd_cod
공식 코드https://github.com/sauradip/muppet
공식 코드https://github.com/tmiu/itfa
공식 코드Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach
https://github.com/ucbdrive/few-shot-object-detection
공식 코드https://github.com/vinairesearch/counting-detr
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.