paper-with-me

홈 › Papers

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

2020-01-09 · CVPR 2020 6 · Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram

Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are absent. This work focuses on addressing such contextual biases to improve the robustness of the learnt feature representations. Our goal is to accurately recognize a category in the absence of its context, without compromising on performance when it co-occurs with context. Our key idea is to decorrelate feature representations of a category from its co-occurring context. We achieve this by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature subspace that represents both categories and context. Our very simple yet effective method is extensible to two multi-label tasks -- object and attribute classification. On 4 challenging datasets, we demonstrate the effectiveness of our method in reducing contextual bias.

📄 PDF Abstract BibTeX arXiv:2001.03152

Code (1)

princetonvisualai/ContextualBias pytorch

Tasks

Attribute

Similar Papers 제목 키워드 기반

Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings

2025-03-19 · Austin Xu, Srijan Bansal, Yifei Ming, Semih Yavuz 외

The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge model…

Instruction FollowingLarge Language ModelRAGRetrieval-augmented Generation

Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss

2024-06-23 · Muhammad Shakeel, Yui Sudo, Yifan Peng, Shinji Watanabe

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these appro…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

2026-05-24 · Xianglin Yang, Bryan Hooi, Gelei Deng, Tianwei Zhang 외 arxiv

The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulnerability. In this work, we introduce BITE (BIas exploraTion and Exploit…

[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

2021-04-28 · RC 2020 · Sunnie S. Y. Kim, Sharon Zhang, Nicole Meister, Olga Russakovsky

Scope of Reproducibility Singh et al. [1] point out the dangers of contextual bias in visual recognition datasets. They propose two methods, CAM-based and feature-split, that better recognize an object or attribute in …

AttributeGPU

Human Perception of Performance

2017-12-05 · Luca Pappalardo, Paolo Cintia, Dino Pedreschi, Fosca Giannotti 외

Humans are routinely asked to evaluate the performance of other individuals, separating success from failure and affecting outcomes from science to education and sports. Yet, in many contexts, the metrics driving the hum…