lim142857 / Sparsifiner
Demo code for CVPR2023 paper "Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers"
☆12Updated last year
Alternatives and similar repositories for Sparsifiner:
Users that are interested in Sparsifiner are comparing it to the libraries listed below
- [NeurIPS2023]Lightweight Vision Transformer with Bidirectional Interaction☆23Updated last year
- This is the official code for paper: Token Summarisation for Efficient Vision Transformers via Graph-based Token Propagation☆26Updated last year
- Adaptive Split-Fusion Transformer (ICME 2023 Oral)☆15Updated 11 months ago
- open source the research work for published on arxiv. https://arxiv.org/abs/2106.02689☆51Updated 2 years ago
- ☆27Updated 2 years ago
- Pytorch implementation of Mix-Shifting-MLP (MS-MLP)☆16Updated 2 years ago
- A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction☆34Updated last year
- The code for ICCV2021 Light Field Saliency Detection with Dual Local Graph Learning and Reciprocative Guidance☆12Updated 2 years ago
- code for paper "Masked Frequency Modeling for Self-Supervised Visual Pre-Training" (https://arxiv.org/pdf/2206.07706.pdf)☆24Updated last year
- [ECCV 2022] AMixer: Adaptive Weight Mixing for Self-attention Free Vision Transformers☆28Updated 2 years ago
- Adaptive Convolutions with Per-pixel Dynamic Filter Atom☆25Updated 3 years ago
- Lightweight Transformer for Multi-modal Tasks☆15Updated 2 years ago
- Trainable Highly-expressive Activation Functions. ECCV 2024☆37Updated 2 months ago
- Multi-modal learning for light field salient object segmentation☆14Updated last year
- ☆29Updated 4 months ago
- ☆14Updated 7 months ago
- Description： Frequency Augmented Variational Autoencoder for better Image Reconstruction☆35Updated last year
- Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution☆25Updated last year
- [CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong C…☆25Updated 2 years ago
- Information Bottleneck Approach to Spatial Attention Learning, IJCAI2021☆14Updated 3 years ago
- [ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wen…☆78Updated last year
- How Much Position Information Do Convolutional Neural Networks Encode?☆11Updated 3 years ago
- Official implementation of "Positional-encoding Image Prior" (PIP)☆13Updated last year
- Code for ICLR 2022 paper. "Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection".☆16Updated 2 years ago
- Codes for our paper "DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer" (KBS 2022)☆16Updated 2 years ago
- Official implementation of ParCNetV2☆10Updated 10 months ago
- EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm☆31Updated 2 years ago
- Multi-head Recurrent Layer Attention for Vision Network☆19Updated last year
- ☆20Updated 2 years ago
- Implementation of HAT https://arxiv.org/pdf/2204.00993☆48Updated 10 months ago