Integrating Text and Image Pre-training for Multi-modal Algorithmic Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zijian, Liu, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913381943869440
author Zhang, Zijian
Liu, Wei
author_facet Zhang, Zijian
Liu, Wei
contents In this paper, we present our solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024. Unlike traditional visual questions and answer tasks, this challenge evaluates abstraction, deduction and generalization ability of neural network in solving visuo-linguistic puzzles designed for specially children in the 6-8 age group. Our model is based on two pre-trained models, dedicated to extract features from text and image respectively. To integrate the features from different modalities, we employed a fusion layer with attention mechanism. We explored different text and image pre-trained models, and fine-tune the integrated classifier on the SMART-101 dataset. Experiment results show that under the data splitting style of puzzle split, our proposed integrated classifier achieves superior performance, verifying the effectiveness of multi-modal pre-trained representations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05318
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Integrating Text and Image Pre-training for Multi-modal Algorithmic Reasoning
Zhang, Zijian
Liu, Wei
Computer Vision and Pattern Recognition
Artificial Intelligence
In this paper, we present our solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024. Unlike traditional visual questions and answer tasks, this challenge evaluates abstraction, deduction and generalization ability of neural network in solving visuo-linguistic puzzles designed for specially children in the 6-8 age group. Our model is based on two pre-trained models, dedicated to extract features from text and image respectively. To integrate the features from different modalities, we employed a fusion layer with attention mechanism. We explored different text and image pre-trained models, and fine-tune the integrated classifier on the SMART-101 dataset. Experiment results show that under the data splitting style of puzzle split, our proposed integrated classifier achieves superior performance, verifying the effectiveness of multi-modal pre-trained representations.
title Integrating Text and Image Pre-training for Multi-modal Algorithmic Reasoning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.05318