Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains

NeurIPS 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing

Read the paperCheck your idea against 108,967 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.

Argues that marginal class and domain balance can hide skewed class-domain joint allocations in multi-domain visual data, and studies how this domain-conditioned imbalance affects recognition.

Problem

Multi-domain unlabeled image collections are often built to balance marginal class totals and domain sizes, but this can still hide highly skewed class-by-domain sample allocations that harm visual recognition.

Approach

Shows that global (marginal) class balance is insufficient in multi-domain data because joint class-domain allocations can be highly skewed even when both marginals are balanced, and frames this as domain-conditioned class imbalance.

Surprising findings

• Marginally balanced class and domain totals can still conceal highly skewed class-domain joint allocations.

Closest papers by meaning

• Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data (AAAI 2024 · similarity 0.89)
• Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts (ICML 2025 · similarity 0.87)
• CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.87)
• BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.86)
• Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance (ICML 2024 · similarity 0.86)
• Gradient Reweighting: Towards Imbalanced Class-Incremental Learning (CVPR 2024 · similarity 0.86)