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
Implementation of "Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner"

Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner This repository is the official implementation of Meta-rPPG: Remote Heart Ra

Eugene Lee 137 Dec 13, 2022
Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

BasicVSR_PlusPlus (CVPR 2022) [Paper] [Project Page] [Code] This is the official repository for BasicVSR++. Please feel free to raise issue related to

Kelvin C.K. Chan 227 Jan 01, 2023
Pytorch reimplementation of the Mixer (MLP-Mixer: An all-MLP Architecture for Vision)

MLP-Mixer Pytorch reimplementation of Google's repository for the MLP-Mixer (Not yet updated on the master branch) that was released with the paper ML

Eunkwang Jeon 18 Dec 08, 2022
Implemented fully documented Particle Swarm Optimization algorithm (basic model with few advanced features) using Python programming language

Implemented fully documented Particle Swarm Optimization (PSO) algorithm in Python which includes a basic model along with few advanced features such as updating inertia weight, cognitive, social lea

9 Nov 29, 2022
Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition"

RandWireNN Unofficial PyTorch Implementation of: Exploring Randomly Wired Neural Networks for Image Recognition. Results Validation result on Imagenet

Seung-won Park 684 Nov 02, 2022
Phylogeny Partners

Phylogeny-Partners Two states models Instalation You may need to install the cython, networkx, numpy, scipy package: pip install cython, networkx, num

1 Sep 19, 2022
Code implementation from my Medium blog post: [Transformers from Scratch in PyTorch]

transformer-from-scratch Code for my Medium blog post: Transformers from Scratch in PyTorch Note: This Transformer code does not include masked attent

Frank Odom 27 Dec 21, 2022
Generate high quality pictures. GAN. Generative Adversarial Networks

ESRGAN generate high quality pictures. GAN. Generative Adversarial Networks """ Super-resolution of CelebA using Generative Adversarial Networks. The

Lieon 1 Dec 14, 2021
[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo Lukas Koestler1*    Nan Yang1,2*,†    Niclas Zeller2,3    Daniel Cremers1

TUM Computer Vision Group 744 Jan 04, 2023
RL-driven agent playing tic-tac-toe on starknet against challengers.

tictactoe-on-starknet RL-driven agent playing tic-tac-toe on starknet against challengers. GUI reference: https://pythonguides.com/create-a-game-using

21 Jul 30, 2022
Using pretrained language models for biomedical knowledge graph completion.

LMs for biomedical KG completion This repository contains code to run the experiments described in: Scientific Language Models for Biomedical Knowledg

Rahul Nadkarni 41 Nov 30, 2022
A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

Manas Sharma 19 Feb 28, 2022
Learned model to estimate number of distinct values (NDV) of a population using a small sample.

Learned NDV estimator Learned model to estimate number of distinct values (NDV) of a population using a small sample. The model approximates the maxim

2 Nov 21, 2022
FeTaQA: Free-form Table Question Answering

FeTaQA: Free-form Table Question Answering FeTaQA is a Free-form Table Question Answering dataset with 10K Wikipedia-based {table, question, free-form

Language, Information, and Learning at Yale 40 Dec 13, 2022
PyTorch implementation of Asymmetric Siamese (https://arxiv.org/abs/2204.00613)

Asym-Siam: On the Importance of Asymmetry for Siamese Representation Learning This is a PyTorch implementation of the Asym-Siam paper, CVPR 2022: @inp

Meta Research 89 Dec 18, 2022
T-LOAM: Truncated Least Squares Lidar-only Odometry and Mapping in Real-Time

T-LOAM: Truncated Least Squares Lidar-only Odometry and Mapping in Real-Time The first Lidar-only odometry framework with high performance based on tr

Pengwei Zhou 183 Dec 01, 2022
🏖 Keras Implementation of Painting outside the box

Keras implementation of Image OutPainting This is an implementation of Painting Outside the Box: Image Outpainting paper from Standford University. So

Bendang 1.1k Dec 10, 2022
CARL provides highly configurable contextual extensions to several well-known RL environments.

CARL (context adaptive RL) provides highly configurable contextual extensions to several well-known RL environments.

AutoML-Freiburg-Hannover 51 Dec 28, 2022
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)

Introduction Yolov5-face is a real-time,high accuracy face detection. Performance Single Scale Inference on VGA resolution(max side is equal to 640 an

DeepCam Shenzhen 1.4k Jan 07, 2023
This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

MPMAB_BEACON This is code used for the paper "Decentralized Multi-player Multi-armed Bandits: Beyond Linear Reward Functions", Neurips 2021. Requireme

Cong Shen Research Group 0 Oct 26, 2021