BrunoSauvalle / AST
Original implementation of the AST model described in the paper "Unsupervised Multi-object Segmentation Using Attention and Soft-argmax"
☆15Updated last year
Alternatives and similar repositories for AST:
Users that are interested in AST are comparing it to the libraries listed below
- [CVPR 2024 Highlight] SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers☆57Updated 7 months ago
- Official code for Slot-Transformer for Videos (STEVE)☆49Updated 2 years ago
- This repository is the official implementation of Improving Object-centric Learning With Query Optimization☆50Updated last year
- [ICML 2022] Official PyTorch implementation of the paper "Unsupervised Image Representation Learning with Deep Latent Particles"☆26Updated last year
- Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns☆16Updated 2 years ago
- Official Code for Neural Systematic Binder☆30Updated last year
- ☆23Updated 2 years ago
- Official implementation of: "Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions" by Villar-Corrales et al…☆15Updated last year
- ` google-research / slot-attention-video ` but in pytorch.☆18Updated 2 years ago
- ☆158Updated last year
- ☆30Updated last year
- Code for NeurIPS 2022 paper "Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space"☆19Updated last year
- Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations ICCV23☆26Updated last month
- ☆43Updated last year
- Slot-TTA shows that test-time adaptation using slot-centric models can improve image segmentation on out-of-distribution examples.☆26Updated last year
- [ICLR 2022] RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning☆64Updated 2 years ago
- Official code release for the ObSuRF model☆32Updated 2 years ago
- Pytorch implementation of "TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut"☆56Updated 2 years ago
- Official implementation of MOST: Multiple object localization with self-supervised transformers published at ICCV 2023☆17Updated 10 months ago
- 🔥Benchmarking Unsupervised Obj Seg (NeurIPS 2022 & IJCV 2024)☆34Updated 3 months ago
- Independent PyTorch Implementation of Object Scene Representation Transformer☆46Updated last year
- Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoenco…☆179Updated 3 years ago
- ☆10Updated 9 months ago
- ☆55Updated 2 months ago
- Repository for our paper "Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities"☆19Updated 8 months ago
- ☆72Updated last year
- [NeurIPS 2022] code for "Visual Concepts Tokenization"☆21Updated 2 years ago
- This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long …☆74Updated 8 months ago
- Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models☆104Updated last year
- ☆73Updated 2 years ago