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

by   Fawaz Sammani, et al.
Vrije Universiteit Brussel

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


page 4

page 8

page 10

page 11


Unifying Vision-and-Language Tasks via Text Generation

Existing methods for vision-and-language learning typically require desi...

e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks

Recently, an increasing number of works have introduced models capable o...

CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations

Providing explanations in the context of Visual Question Answering (VQA)...

Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling

In this paper, we propose UNICORN, a vision-language (VL) model that uni...

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

We introduce UniLoss, a unified framework to generate surrogate losses f...

Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis

Large Language Models (LLMs) have demonstrated great capabilities in sol...

SPECTRA: Sparse Structured Text Rationalization

Selective rationalization aims to produce decisions along with rationale...

Please sign up or login with your details

Forgot password? Click here to reset