mlvlab / MCTF
Official implementation of CVPR 2024 paper "Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers".
☆27Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for MCTF
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆31Updated last year
- [NeurIPS2024 Spotlight] The official implementation of GrootVL: Tree Topology is All You Need in State Space Model☆83Updated 5 months ago
- ☆32Updated last year
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆70Updated 3 months ago
- [CVPR2024] The code of "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory"☆64Updated last month
- ☆22Updated 5 months ago
- [ICCV 2023] Generative Prompt Model for Weakly Supervised Object Localization☆55Updated last year
- This repository is the official implementation of our Autoregressive Pretraining with Mamba in Vision☆64Updated 5 months ago
- [2024 ECCV Workshop] Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion☆30Updated last month
- CVPR2024: Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models☆60Updated 4 months ago
- [CVPR 2024] Official implementation of "Adapters Strike Back"☆32Updated 4 months ago
- [ECCV2024] ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference☆65Updated 3 months ago
- Robust Referring Video Object Segmentation with Cyclic Structural Consistency [ICCV 2023]☆25Updated 8 months ago
- Implementation of "VL-Mamba: Exploring State Space Models for Multimodal Learning"☆78Updated 8 months ago
- The official repo for "Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation", ECCV 2024☆12Updated last month
- Official implementation of CVPR 2024 paper "vid-TLDR: Training Free Token merging for Light-weight Video Transformer".