Research map / Label-efficient and robust learning / Recognition and long-tail
Label-Focused Inductive Bias over Latent Object Features in Visual Classification
Ilmin Kang, HyounYoung Bae, Kangil Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper argues that classifiers' input-domain inductive bias can conflict with human label semantics and proposes a label-focused inductive bias over latent object features for visual classification.
Problem
Neural classifiers learn features driven by visual similarity of inputs, which can conflict with unseen label relations defined by human world knowledge in the output domain, limiting generalization.
Approach
Introduces a label-focused inductive bias over latent object features so that learned representations align with output-domain label relations rather than only input-domain visual similarity.
Closest papers by meaning
- A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications (AAAI 2022 · similarity 0.86)
- Training the Untrainable: Introducing Inductive Bias via Representational Alignment (NeurIPS 2025 · similarity 0.86)
- Understanding Bias in Large-Scale Visual Datasets (NeurIPS 2024 · similarity 0.85)
- Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers (CVPR 2025 · similarity 0.85)
- Perceptual Inductive Bias Is What You Need Before Contrastive Learning (CVPR 2025 · similarity 0.85)
- L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
