paper-with-me

홈 › Papers

From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation

2023-11-21 · Jiaxin Ge, Sanjay Subramanian, Trevor Darrell, Boyi Li

Addressing the challenge of adapting pre-trained vision-language models for generating insightful explanations for visual reasoning tasks with limited annotations, we present ReVisE: a $\textbf{Re}$cursive $\textbf{Vis}$ual $\textbf{E}$xplanation algorithm. Our method iteratively computes visual features (conditioned on the text input), an answer, and an explanation, to improve the explanation quality step by step until the answer converges. We find that this multi-step approach guides the model to correct its own answers and outperforms single-step explanation generation. Furthermore, explanations generated by ReVisE also serve as valuable annotations for few-shot self-training. Our approach outperforms previous methods while utilizing merely 5% of the human-annotated explanations across 10 metrics, demonstrating up to a 4.2 and 1.3 increase in BLEU-1 score on the VCR and VQA-X datasets, underscoring the efficacy and data-efficiency of our method.

📄 PDF Abstract BibTeX arXiv:2311.12391

Code (0)

등록된 구현이 없습니다.

Tasks

Explanation GenerationVisual Question Answering (VQA)Visual Reasoning

Similar Papers 제목 키워드 기반

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong

2023-10-19 · Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao 외

Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get…

Fact CheckingInformation Retrieval

Right for the Right Reason: Making Image Classification Robust

2020-07-23 · Anna Nguyen, Adrian Oberföll, Michael Färber

The effectiveness of Convolutional Neural Networks (CNNs)in classifying image data has been thoroughly demonstrated. In order to explain the classification to humans, methods for visualizing classification evidence have …

ClassificationGeneral Classificationimage-classificationImage Classification+3

RIV: Recursive Introspection Mask Diffusion Vision Language Model

2025-09-28 · YuQian Li, Limeng Qiao, Lin Ma arxiv

Mask Diffusion-based Vision Language Models (MDVLMs) have achieved remarkable progress in multimodal understanding tasks. However, these models are unable to correct errors in generated tokens, meaning they lack self-cor…

Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making

2023-08-08 · Min Hun Lee, Chong Jun Chew

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestio…

counterfactualDecision Making

Right on Time: Revising Time Series Models by Constraining their Explanations

2024-02-20 · Maurice Kraus, David Steinmann, Antonia Wüst, Andre Kokozinski 외

The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to incorrect outputs. Our newly recorded, naturally confounded dataset named P2S from a rea…

Time SeriesTime Series Classification