An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

Overview

Bottom-Up and Top-Down Attention for Visual Question Answering

An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

The implementation follows the VQA system described in "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering" (https://arxiv.org/abs/1707.07998) and "Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge" (https://arxiv.org/abs/1708.02711).

Results

Model Validation Accuracy Training Time
Reported Model 63.15 12 - 18 hours (Tesla K40)
Implemented Model 63.58 40 - 50 minutes (Titan Xp)

The accuracy was calculated using the VQA evaluation metric.

About

This is part of a project done at CMU for the course 11-777 Advanced Multimodal Machine Learning and a joint work between Hengyuan Hu, Alex Xiao, and Henry Huang.

As part of our project, we implemented bottom up attention as a strong VQA baseline. We were planning to integrate object detection with VQA and were very glad to see that Peter Anderson and Damien Teney et al. had already done that beautifully. We hope this clean and efficient implementation can serve as a useful baseline for future VQA explorations.

Implementation Details

Our implementation follows the overall structure of the papers but with the following simplifications:

  1. We don't use extra data from Visual Genome.
  2. We use only a fixed number of objects per image (K=36).
  3. We use a simple, single stream classifier without pre-training.
  4. We use the simple ReLU activation instead of gated tanh.

The first two points greatly reduce the training time. Our implementation takes around 200 seconds per epoch on a single Titan Xp while the one described in the paper takes 1 hour per epoch.

The third point is simply because we feel the two stream classifier and pre-training in the original paper is over-complicated and not necessary.

For the non-linear activation unit, we tried gated tanh but couldn't make it work. We also tried gated linear unit (GLU) and it works better than ReLU. Eventually we choose ReLU due to its simplicity and since the gain from using GLU is too small to justify the fact that GLU doubles the number of parameters.

With these simplifications we would expect the performance to drop. For reference, the best result on validation set reported in the paper is 63.15. The reported result without extra data from visual genome is 62.48, the result using only 36 objects per image is 62.82, the result using two steam classifier but not pre-trained is 62.28 and the result using ReLU is 61.63. These numbers are cited from the Table 1 of the paper: "Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge". With all the above simplification aggregated, our first implementation got around 59-60 on validation set.

To shrink the gap, we added some simple but powerful modifications. Including:

  1. Add dropout to alleviate overfitting
  2. Double the number of neurons
  3. Add weight normalization (BN seems not work well here)
  4. Switch to Adamax optimizer
  5. Gradient clipping

These small modifications bring the number back to ~62.80. We further change the concatenation based attention module in the original paper to a projection based module. This new attention module is inspired by the paper "Modeling Relationships in Referential Expressions with Compositional Modular Networks" (https://arxiv.org/pdf/1611.09978.pdf), but with some modifications (implemented in attention.NewAttention). With the help of this new attention, we boost the performance to ~63.58, surpassing the reported best result with no extra data and less computation cost.

Usage

Prerequisites

Make sure you are on a machine with a NVIDIA GPU and Python 2 with about 70 GB disk space.

  1. Install PyTorch v0.3 with CUDA and Python 2.7.
  2. Install h5py.

Data Setup

All data should be downloaded to a 'data/' directory in the root directory of this repository.

The easiest way to download the data is to run the provided script tools/download.sh from the repository root. The features are provided by and downloaded from the original authors' repo. If the script does not work, it should be easy to examine the script and modify the steps outlined in it according to your needs. Then run tools/process.sh from the repository root to process the data to the correct format.

Training

Simply run python main.py to start training. The training and validation scores will be printed every epoch, and the best model will be saved under the directory "saved_models". The default flags should give you the result provided in the table above.

Owner
Hengyuan Hu
Hengyuan Hu
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning This repository is official Tensorflow implementation of paper: Ensemb

Seunghyun Lee 12 Oct 18, 2022
Simultaneous Detection and Segmentation

Simultaneous Detection and Segmentation This is code for the ECCV Paper: Simultaneous Detection and Segmentation Bharath Hariharan, Pablo Arbelaez,

Bharath Hariharan 96 Jul 20, 2022
Modular Probabilistic Programming on MXNet

MXFusion | | | | Tutorials | Documentation | Contribution Guide MXFusion is a modular deep probabilistic programming library. With MXFusion Modules yo

Amazon 100 Dec 10, 2022
Unofficial Implementation of RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series (AAAI 2019)

RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series (AAAI 2019) This repository contains python (3.5.2) implementation of

Doyup Lee 222 Dec 21, 2022
This project uses Template Matching technique for object detecting by detection of template image over base image.

Object Detection Project Using OpenCV This project uses Template Matching technique for object detecting by detection the template image over base ima

Pratham Bhatnagar 7 May 29, 2022
Get started learning C# with C# notebooks powered by .NET Interactive and VS Code.

.NET Interactive Notebooks for C# Welcome to the home of .NET interactive notebooks for C#! How to Install Download the .NET Coding Pack for VS Code f

.NET Platform 425 Dec 25, 2022
Code for "Learning Graph Cellular Automata"

Learning Graph Cellular Automata This code implements the experiments from the NeurIPS 2021 paper: "Learning Graph Cellular Automata" Daniele Grattaro

Daniele Grattarola 37 Oct 26, 2022
PyTorch implementation of MuseMorphose, a Transformer-based model for music style transfer.

MuseMorphose This repository contains the official implementation of the following paper: Shih-Lun Wu, Yi-Hsuan Yang MuseMorphose: Full-Song and Fine-

Yating Music, Taiwan AI Labs 142 Jan 08, 2023
Official implementation of SynthTIGER (Synthetic Text Image GEneratoR) ICDAR 2021

🐯 SynthTIGER: Synthetic Text Image GEneratoR Official implementation of SynthTIGER | Paper | Datasets Moonbin Yim1, Yoonsik Kim1, Han-cheol Cho1, Sun

Clova AI Research 256 Jan 05, 2023
Annotate datasets with a semi-trained or fully trained YOLOv5 model

YOLOv5 Auto Annotator Annotate datasets with a semi-trained or fully trained YOLOv5 model Prerequisites Ubuntu =20.04 Python =3.7 System dependencie

Akash James 3 May 14, 2022
Probabilistic Gradient Boosting Machines

PGBM Probabilistic Gradient Boosting Machines (PGBM) is a probabilistic gradient boosting framework in Python based on PyTorch/Numba, developed by Air

Olivier Sprangers 112 Dec 28, 2022
Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face Manipulation" published in CVPR 2020.

FFD Source Code Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face M

88 Nov 22, 2022
Low Complexity Channel estimation with Neural Network Solutions

Interpolation-ResNet Invited paper for WSA 2021, called 'Low Complexity Channel estimation with Neural Network Solutions'. Low complexity residual con

Dianxin 10 Dec 10, 2022
A PyTorch implementation of unsupervised SimCSE

A PyTorch implementation of unsupervised SimCSE

99 Dec 23, 2022
PyTorch implementation of hand mesh reconstruction described in CMR and MobRecon.

Hand Mesh Reconstruction Introduction This repo is the PyTorch implementation of hand mesh reconstruction described in CMR and MobRecon. Update 2021-1

Xingyu Chen 236 Dec 29, 2022
nn_builder lets you build neural networks with less boilerplate code

nn_builder lets you build neural networks with less boilerplate code. You specify the type of network you want and it builds it. Install pip install n

Petros Christodoulou 157 Nov 20, 2022
PyTorch implementation of paper "StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement" (ICCV 2021 Oral)

StarEnhancer StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement (ICCV 2021 Oral) Abstract: Image enhancement is a subjective process w

IDKiro 133 Dec 28, 2022
Nest Protect integration for Home Assistant. This will allow you to integrate your smoke, heat, co and occupancy status real-time in HA.

Nest Protect integration for Home Assistant Custom component for Home Assistant to interact with Nest Protect devices via an undocumented and unoffici

Mick Vleeshouwer 175 Dec 29, 2022
A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning This is a small repo illustrating how to use WebDataset on ImageNet. usi

50 Dec 16, 2022
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

Bayesian Neural Networks Pytorch implementations for the following approximate inference methods: Bayes by Backprop Bayes by Backprop + Local Reparame

1.4k Jan 07, 2023