paper-with-me

홈 › Papers

Play Fair: Frame Attributions in Video Models

2020-11-24 · Will Price, Dima Damen

In this paper, we introduce an attribution method for explaining action recognition models. Such models fuse information from multiple frames within a video, through score aggregation or relational reasoning. We break down a model's class score into the sum of contributions from each frame, fairly. Our method adapts an axiomatic solution to fair reward distribution in cooperative games, known as the Shapley value, for elements in a variable-length sequence, which we call the Element Shapley Value (ESV). Critically, we propose a tractable approximation of ESV that scales linearly with the number of frames in the sequence. We employ ESV to explain two action recognition models (TRN and TSN) on the fine-grained dataset Something-Something. We offer detailed analysis of supporting/distracting frames, and the relationships of ESVs to the frame's position, class prediction, and sequence length. We compare ESV to naive baselines and two commonly used feature attribution methods: Grad-CAM and Integrated-Gradients.

📄 PDF Abstract BibTeX arXiv:2011.12372

Code (1)

willprice/play-fair 공식 구현 pytorch

Tasks

Action RecognitionRelational Reasoning

Similar Papers 제목 키워드 기반

Influence-based Attributions can be Manipulated

2024-09-08 · Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic ince…

Data ValuationFairness

Mitigating Bias Using Model-Agnostic Data Attribution

2024-05-08 · Sander De Coninck, Wei-Cheng Wang, Sam Leroux, Pieter Simoens

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regula…

Fairnessmodel

Explaining Risks: Axiomatic Risk Attributions for Financial Models

2025-06-07 · Dangxing Chen

In recent years, machine learning models have achieved great success at the expense of highly complex black-box structures. By using axiomatic attribution methods, we can fairly allocate the contributions of each feature…

Attributing Fair Decisions with Attention Interventions

2021-09-08 · NAACL (TrustNLP) 2022 7 · Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg 외

The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness …

Decision MakingFairness

FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs

2025-08-25 · Bingkang Shi, Jen-tse Huang, Long Luo, Tianyu Zong 외 arxiv

Large Language Models (LLMs) have increasingly enhanced or replaced traditional Non-Player Characters (NPCs) in video games. However, these LLM-based NPCs inherit underlying social biases (e.g., race or class), posing fa…