CARE is a parameter-efficient framework that aggregates predictions from noisy labels, VLM text embeddings, and visual features with class-frequency-based agreement thresholds to rectify labels in long-tailed noisy datasets.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance.
citing papers explorer
-
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
CARE is a parameter-efficient framework that aggregates predictions from noisy labels, VLM text embeddings, and visual features with class-frequency-based agreement thresholds to rectify labels in long-tailed noisy datasets.
-
Image-aware Layout Generation with User Constraints for Poster Design
A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance.
- Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?