https://github.com/jinyangyuan/genesis
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
Papers with Code 아카이브
Object Discovery
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Object Discovery is the task of identifying previously unseen objects.
Source: Unsupervised Object Discovery and Segmentation of RGBD-images
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/katieluo88/drift
Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery
https://github.com/kostadinovshalon/oln-ssos
Learning Open-World Object Proposals without Learning to Classify
https://github.com/locuslab/massive-activations
https://github.com/lucidrains/slot-attention
https://github.com/lukemelas/deep-spectral-segmentation
Localizing Objects with Self-Supervised Transformers and no Labels
https://github.com/mb010/AstroAttention
https://github.com/nickjiang2378/test-time-registers
https://github.com/nizarmassouh/WebDB
Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work
https://github.com/rwightman/pytorch-image-models
https://github.com/stelzner/monet
https://github.com/theostoican/Guided-Research/blob/main/finetuning_odin_resnet.ipynb
https://github.com/tianaidong/2021splu-robonlp-vispa
GuessWhat?! Visual object discovery through multi-modal dialogue
https://github.com/tosshero/3d_perception
Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset
https://github.com/untitled-ai/slot_attention
https://github.com/vision4robotics/SiameseTracking4UAV
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
https://github.com/vlar-group/unmore
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers
https://github.com/wangyongjie-ntu/Learn-to-pay-attention
https://github.com/zhanyang-nwpu/rsvg-pytorch
GuessWhat?! Visual object discovery through multi-modal dialogue
https://gitlab.com/birder/birder
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.