Official Pytorch Implementation of Relational Self-Attention: What's Missing in Attention for Video Understanding

Related tags

Deep Learning RSA
Overview

Relational Self-Attention: What's Missing in Attention for Video Understanding

This repository is the official implementation of "Relational Self-Attention: What's Missing in Attention for Video Understanding" by Manjin Kim*, Heeseung Kwon*, Chunyu Wang, Suha Kwak, and Minsu Cho (*equal contribution).

RSA

Requirements

  • Python: 3.7.9
  • Pytorch: 1.6.0
  • TorchVision: 0.2.1
  • Cuda: 10.1
  • Conda environment environment.yml

To install requirements:

    conda env create -f environment.yml
    conda activate rsa

Dataset Preparation

  1. Download Something-Something v1 & v2 (SSv1 & SSv2) datasets and extract RGB frames. Download URLs: SSv1, SSv2
  2. Make txt files that define training & validation splits. Each line in txt files is formatted as [video_path] [#frames] [class_label]. Please refer to any txt files in ./data directory.

Training

To train RSANet-R50 on SSv1 or SSv2 datasets in the paper, run this command:

    # For SSv1
    ./scripts/train_Something_v1.sh 
    
    
     
    # example: ./scripts/train_Something_v1.sh RSA_R50_SSV1_16frames 16
    
    # For SSv2
    ./scripts/train_Something_v2.sh 
      
      
       
    # example: ./scripts/train_Something_v2.sh RSA_R50_SSV2_16frames 16

Evaluation

To evaluate RSANet-R50 on SSv2 dataset in the paper, run:

    # For SSv1
    ./scripts/test_Something_v1.sh 
    
     
     
      
    # example: ./scripts/test_Something_v1.sh RSA_R50_SSV1_16frames resnet_rgb_model_best.pth.tar 16
    
    # For SSv2
    ./scripts/test_Something_v2.sh 
       
        
        
          # example: ./scripts/test_Something_v2.sh RSA_R50_SSV2_16frames resnet_rgb_model_best.pth.tar 16

Results

Our model achieves the following performance on Something-Something-V1 and Something-Something-V2:

model dataset frames top-1 / top-5 logs checkpoints
RSANet-R50 SSV1 16 54.0 % / 81.1 % [log] [checkpoint]
RSANet-R50 SSV2 16 66.0 % / 89.9 % [log] [checkpoint]

Qualitative Results

kernel_visualization

You might also like...
An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)
An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

Kakao Brain 72 Dec 28, 2022
[CVPR 2022] Official PyTorch Implementation for
[CVPR 2022] Official PyTorch Implementation for "Reference-based Video Super-Resolution Using Multi-Camera Video Triplets"

Reference-based Video Super-Resolution (RefVSR) Official PyTorch Implementation of the CVPR 2022 Paper Project | arXiv | RealMCVSR Dataset This repo c

Junyong Lee 151 Dec 30, 2022
Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The original code is written in keras.

CasRel-pytorch-reimplement Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The o

longlongman 170 Dec 1, 2022
The implementation of CVPR2021 paper Temporal Query Networks for Fine-grained Video Understanding, by Chuhan Zhang, Ankush Gupta and Andrew Zisserman.
The implementation of CVPR2021 paper Temporal Query Networks for Fine-grained Video Understanding, by Chuhan Zhang, Ankush Gupta and Andrew Zisserman.

Temporal Query Networks for Fine-grained Video Understanding šŸ“‹ This repository contains the implementation of CVPR2021 paper Temporal_Query_Networks

null 55 Dec 21, 2022
This folder contains the implementation of the multi-relational attribute propagation algorithm.

MrAP This folder contains the implementation of the multi-relational attribute propagation algorithm. It requires the package pytorch-scatter. Please

null 6 Dec 6, 2022
Implementation of the šŸ˜‡ Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Implementation of the šŸ˜‡ Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

HaloNet - Pytorch Implementation of the Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones. This re

Phil Wang 189 Nov 22, 2022
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(nĀ²) Memory"

Memory Efficient Attention Pytorch Implementation of a memory efficient multi-head attention as proposed in the paper, Self-attention Does Not Need O(

Phil Wang 180 Jan 5, 2023
Official PyTorch code of Holistic 3D Scene Understanding from a Single Image with Implicit Representation (CVPR 2021)
Official PyTorch code of Holistic 3D Scene Understanding from a Single Image with Implicit Representation (CVPR 2021)

Implicit3DUnderstanding (Im3D) [Project Page] Holistic 3D Scene Understanding from a Single Image with Implicit Representation Cheng Zhang, Zhaopeng C

Cheng Zhang 149 Jan 8, 2023
Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).
Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).

DeepPanoContext (DPC) [Project Page (with interactive results)][Paper] DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context G

Cheng Zhang 66 Nov 16, 2022
Comments
  • Performance on SSV1-frame8

    Performance on SSV1-frame8

    Hello, thanks for your great work. I have great interest and want to reproduce it. But I can not get a comparable result on SSV1 when using 8 frames, that our reproduced result is 50.6 while it is 51.9 in your paper. All the settings are the same in this repo. We guess it may caused by different random seed.

    Could you please provide the checkpoint of 51.9 result? As you only provide the ckpt under 16 frames' setting.

    Thx.

    opened by Sobeney 0
  • FOR sepcific version

    FOR sepcific version

    Hello, after reading your article about RSA recently, I have great interest and want to reproduce it. I noticed that the normal use of CUDA has a lot to do with the graphics card model.But I don't know the specific hardware model and software version of this system. May you tell me the version number of GPU and Ubuntu you use

    opened by ChuLinTang 2
Owner
mandos
PH.D. student
mandos
GitHub
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

TimeSformer This is an official pytorch implementation of Is Space-Time Attention All You Need for Video Understanding?. In this repository, we provid

Facebook Research 1k Dec 31, 2022
(ICCV'21) Official PyTorch implementation of Relational Embedding for Few-Shot Classification

Relational Embedding for Few-Shot Classification (ICCV 2021) Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho [paper], [project hompage] We propose t

Dahyun Kang 82 Dec 24, 2022
[ICCV 2021] Official PyTorch implementation for Deep Relational Metric Learning.

Deep Relational Metric Learning This repository is the official PyTorch implementation of Deep Relational Metric Learning. Framework Datasets CUB-200-

Borui Zhang 39 Dec 10, 2022
ReSSL: Relational Self-Supervised Learning with Weak Augmentation

ReSSL: Relational Self-Supervised Learning with Weak Augmentation This repository contains PyTorch evaluation code, training code and pretrained model

mingkai 45 Oct 25, 2022
ReLoss - Official implementation for paper "Relational Surrogate Loss Learning" ICLR 2022

Relational Surrogate Loss Learning (ReLoss) Official implementation for paper "R

Tao Huang 31 Nov 22, 2022
Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms

LESA Introduction This repository contains the official implementation of Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Cont

Chenglin Yang 20 Dec 31, 2021
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

PySlowFast PySlowFast is an open source video understanding codebase from FAIR that provides state-of-the-art video classification models with efficie

Meta Research 5.3k Jan 3, 2023
PyTorch implementation of DirectCLR from paper Understanding Dimensional Collapse in Contrastive Self-supervised Learning

DirectCLR DirectCLR is a simple contrastive learning model for visual representation learning. It does not require a trainable projector as SimCLR. It

Meta Research 49 Dec 21, 2022
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.

relational-rnn-pytorch An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch. Relational Memory Core (

Sang-gil Lee 241 Nov 18, 2022
A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Torch-RGCN Torch-RGCN is a PyTorch implementation of the RGCN, originally proposed by Schlichtkrull et al. in Modeling Relational Data with Graph Conv

Thiviyan Singam 66 Nov 30, 2022