CVJul 26, 2018

Pythia v0.1: the Winning Entry to the VQA Challenge 2018

arXiv:1807.09956v2207 citationsHas Code
Originality Incremental advance
AI Analysis

This work provides incremental improvements for VQA researchers and practitioners by refining an existing model to win a competition.

The paper tackles improving visual question answering (VQA) performance by enhancing the bottom-up top-down model with architectural tweaks, fine-tuning, and data augmentation, achieving a 4.55% increase to 70.22% on VQA v2.0, and further boosting to 72.27% with diverse ensembling.

This document describes Pythia v0.1, the winning entry from Facebook AI Research (FAIR)'s A-STAR team to the VQA Challenge 2018. Our starting point is a modular re-implementation of the bottom-up top-down (up-down) model. We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2.0 dataset -- from 65.67% to 70.22%. Furthermore, by using a diverse ensemble of models trained with different features and on different datasets, we are able to significantly improve over the 'standard' way of ensembling (i.e. same model with different random seeds) by 1.31%. Overall, we achieve 72.27% on the test-std split of the VQA v2.0 dataset. Our code in its entirety (training, evaluation, data-augmentation, ensembling) and pre-trained models are publicly available at: https://github.com/facebookresearch/pythia

Code Implementations9 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes