LeapLabTHU / DAT-Jittor
Jittor implementation of Vision Transformer with Deformable Attention
☆29Updated 2 years ago
Related projects: ⓘ
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆40Updated 4 months ago
- Official implementation of Dynamic Perceiver☆39Updated 10 months ago
- [NeurIPS 2022] Latency-aware Spatial-wise Dynamic Networks☆22Updated last year
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆90Updated last year
- [ECCV 2022] Learning to Weight Samples for Dynamic Early-exiting Networks☆32Updated 11 months ago
- ☆25Updated last year
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆27Updated last week
- ☆88Updated 2 years ago
- ☆16Updated this week
- Official code of paper Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL☆19Updated 10 months ago
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆10Updated last week
- ☆34Updated last year
- [arXiv] Cross-Modal Adapter for Text-Video Retrieval☆53Updated last year
- A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"☆26Updated 3 months ago
- [IEEE TIP] Fine-grained Recognition with Learnable Semantic Data Augmentation☆26Updated 8 months ago
- Official implementation of A Mixture of Surprises for Unsupervised Reinforcement Learning☆21Updated last year
- [ICLR2024] Exploring Target Representations for Masked Autoencoders☆52Updated 8 months ago
- Official Code Release for Container : Context Aggregation Network☆46Updated 2 years ago
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆85Updated last year
- ☆98Updated 6 months ago
- This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".☆118Updated 2 years ago
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- [ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.☆60Updated 11 months ago
- [ICML 2023] MTPD: Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation☆8Updated last year
- PyTorch implementation of the paper "MILAN: Masked Image Pretraining on Language Assisted Representation" https://arxiv.org/pdf/2208.0604…☆79Updated 2 years ago
- (NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping☆95Updated last year
- ☆40Updated last year
- (CVPR 2022) Automated Progressive Learning for Efficient Training of Vision Transformers☆24Updated 2 years ago
- Official implementation of AdaViT☆48Updated 2 years ago
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆163Updated 11 months ago