https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/vild
공식 코드Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
Papers with Code 아카이브
Open Vocabulary Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 4
- 보존된 평가 기록
- 64
Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tgxs002/cora
공식 코드CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
https://github.com/vinairesearch/lp-ovod
공식 코드https://github.com/warlockwendell/aggdet
공식 코드Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
https://github.com/wkfdb/marvelovd
공식 코드https://github.com/wusize/clim
공식 코드CLIM: Contrastive Language-Image Mosaic for Region Representation
https://github.com/wusize/clipself
공식 코드CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
https://github.com/wusize/ovdet
공식 코드Aligning Bag of Regions for Open-Vocabulary Object Detection
https://github.com/xiaofeng94/gen-enhanced-negs
공식 코드Generating Enhanced Negatives for Training Language-Based Object Detectors
https://github.com/xiaofeng94/sas-det
공식 코드https://github.com/xiaofeng94/vl-plm
공식 코드Exploiting Unlabeled Data with Vision and Language Models for Object Detection
https://github.com/xiaomoguhz/ov-dquo
공식 코드https://github.com/xushilin1/dst-det
공식 코드DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
https://github.com/yangyangyang127/pointclip_v2
공식 코드PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
https://github.com/yoctta/xpaste
공식 코드X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
https://github.com/yuhangzang/ov-detr
공식 코드https://github.com/zchuhan/cckt-det
공식 코드Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection
https://github.com/zehong-ma/ovmr
공식 코드OVMR: Open-Vocabulary Recognition with Multi-Modal References
https://github.com/zengyan-97/x-vlm
공식 코드Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
https://github.com/zrrskywalker/pointclip
공식 코드https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/blip2
https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/AndresPMD/Clip_CMR
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/ArsenalCheng/Meta-Adapter
Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
https://github.com/FreddeFrallan/Multilingual-CLIP
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/Gahyeonkim09/AAPL
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/IMvision12/keras-vision-models
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/Kaushalya/medclip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/LONGXUANX/CDFormer_code
Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
https://github.com/MindCode-4/code-2/tree/main/owlvit
https://github.com/NYU-DICE-Lab/open_clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/OML-Team/open-metric-learning
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_CLIP_model.md
Learning Transferable Visual Models From Natural Language Supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.