Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks

TL;DR

Uni-NLX is a unified multi-task model that leverages large language models to generate natural language explanations across vision and vision-language tasks, reducing parameters while maintaining or improving performance.

Contribution

It introduces a unified framework for all NLE tasks, along with two new datasets, enabling multi-task learning with fewer parameters and comparable or better results.

Findings

Capable of performing 7 NLE tasks simultaneously

Uses 7X fewer parameters than task-specific models

Achieves comparable or superior performance on several tasks

Abstract

Natural Language Explanations (NLE) aim at supplementing the prediction of a model with human-friendly natural text. Existing NLE approaches involve training separate models for each downstream task. In this work, we propose Uni-NLX, a unified framework that consolidates all NLE tasks into a single and compact multi-task model using a unified training objective of text generation. Additionally, we introduce two new NLE datasets: 1) ImageNetX, a dataset of 144K samples for explaining ImageNet categories, and 2) VQA-ParaX, a dataset of 123K samples for explaining the task of Visual Question Answering (VQA). Both datasets are derived leveraging large language models (LLMs). By training on the 1M combined NLE samples, our single unified framework is capable of simultaneously performing seven NLE tasks including VQA, visual recognition and visual reasoning tasks with 7X fewer parameters, demonstrating comparable performance to the independent task-specific models in previous approaches, and in certain tasks even outperforming them. Code is at https://github.com/fawazsammani/uni-nlx