Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

Here is the code for ssbassline model. We also provide OCR results/features/models. The code is built on top of M4C, where more detailed information can also be found.

Citation

If you use ssbaseline in your work, please cite:

@article{zhu2020simple,
  title={Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps},
  author={Zhu, Qi and Gao, Chenyu and Wang, Peng and Wu, Qi},
  journal={arXiv preprint arXiv:2012.05153},
  year={2020}
}

Installation

First install the repo using

git clone https://github.com/ZephyrZhuQi/ssbaseline.git ~/ssbaseline
cd ~/ssbaseline
python setup.py build develop

Getting Data

We provide SBD-Trans OCR for TextVQA and ST-VQA datasets. The corresponding OCR Faster R-CNN features and Recog-CNN features are also released.

Datasets	ImDBs	Object Faster R-CNN Features	OCR Faster R-CNN Features	OCR Recog-CNN Features
TextVQA	TextVQA ImDB	Open Images	TextVQA SBD-Trans OCRs	TextVQA SBD-Trans OCRs
ST-VQA	ST-VQA ImDB	ST-VQA Objects	ST-VQA SBD-Trans OCRs	ST-VQA SBD-Trans OCRs

Pretrained Models

We release the following pretrained models for ssbaseline on TextVQA.

For the TextVQA dataset, we release: ssbaseline trained with ST-VQA as additional data (our best model) with SBD-Trans.

Datasets	Config Files (under `configs/vqa/`)	Pretrained Models	Metrics	Notes
TextVQA (`m4c_textvqa`)	`m4c_textvqa/m4c_with_stvqa.yml`	`ssbaseline_with_stvqa`	val accuracy - 45.53%; test accuracy - 45.66%	SBD-Trans OCRs; ST-VQA as additional data

Training and Evaluation

Please follow the M4C README for the training and evaluation of the M4C model on each dataset.

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps[AAAI2021]

Related tags

Overview

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

Citation

Installation

Getting Data

Pretrained Models

Training and Evaluation

Owner

ZephyrZhuQi

95.47% on CIFAR10 with PyTorch

The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

True Few-Shot Learning with Language Models

This is the code for ACL2021 paper A Unified Generative Framework for Aspect-Based Sentiment Analysis

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

Example Of Fine-Tuning BERT For Named-Entity Recognition Task And Preparing For Cloud Deployment Using Flask, React, And Docker

AISTATS 2019: Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in 3D.

Spatial Action Maps for Mobile Manipulation (RSS 2020)

Reproduces the results of the paper "Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations".

A Sign Language detection project using Mediapipe landmark detection and Tensorflow LSTM's

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling @ INTERSPEECH 2021 Accepted

A Research-oriented Federated Learning Library and Benchmark Platform for Graph Neural Networks. Accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.

This repo is developed for Strong Baseline For Vehicle Re-Identification in Track 2 Ai-City-2021 Challenges

City Surfaces: City-scale Semantic Segmentation of Sidewalk Surfaces

Implementation for "Exploiting Aliasing for Manga Restoration" (CVPR 2021)

An index of algorithms for learning causality with data

A library for augmentation of a YOLO-formated dataset

git《Commonsense Knowledge Base Completion with Structural and Semantic Context》(AAAI 2020) GitHub: [fig1]

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022