HankYe / Once-for-Both
[CVPR'24] Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
☆12Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for Once-for-Both
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆87Updated last year
- official implementation of β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search (CVPR22 oral).☆84Updated 2 years ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆19Updated 2 weeks ago
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Pekin…☆52Updated 3 weeks ago
- [NeurIPS 2023] Rank-DETR for High Quality Object Detection☆87Updated last year
- [CVPR 2024] PTQ4SAM: Post-Training Quantization for Segment Anything☆55Updated 4 months ago
- [AAAI 2023] Official PyTorch Code for "Curriculum Temperature for Knowledge Distillation"☆157Updated 4 months ago
- 'NKD and USKD' (ICCV 2023) and 'ViTKD' (CVPRW 2024)☆215Updated last year
- [ICCV2023] DETR Doesn’t Need Multi-Scale or Locality Design☆192Updated 11 months ago
- The official PyTorch implementation of CHEX: CHannel EXploration for CNN Model Compression (CVPR 2022). Paper is available at https://ope…☆37Updated 2 years ago
- [ECCV 2024] Isomorphic Pruning for Vision Models☆53Updated 3 months ago
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆244Updated last year
- A paper list of some recent works about Token Compress for Vit and VLM☆133Updated this week
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆36Updated 3 weeks ago
- [CVPR 2023] PD-Quant: Post-Training Quantization Based on Prediction Difference Metric☆49Updated last year
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆33Updated 2 months ago
- The official implementation of the NeurIPS 2022 paper Q-ViT.☆82Updated last year
- [ICCV2023] DETRDistill: A Universal Knowledge Distillation Framework for DETR-families☆42Updated last year
- PyTorch code and checkpoints release for VanillaKD: https://arxiv.org/abs/2305.15781☆71Updated 11 months ago
- 1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…☆208Updated 2 months ago
- [TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.☆107Updated 10 months ago
- [BMVC 2024] Official implementation of Align-DETR☆49Updated 3 months ago
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆30Updated last year
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆40Updated last month
- ☆27Updated last year
- ☆82Updated 4 months ago
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆172Updated last year
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.☆98Updated last year
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆40Updated 6 months ago