Proposes CFRG noise schedule for diffusion models that assigns larger noises to low-frequency classes to improve generation on imbalanced datasets.
Long-tailed recognition by routing diverse distribution-aware experts
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Loss reweighting is cast as an inverse problem that dynamically infers class weights to equalize per-class average losses under the Neural Collapse simplex ETF target.
DeCon decouples LTSSL into head-class and tail-class branches that interact and converge, delivering SOTA accuracy on mismatched-distribution benchmarks and outperforming prior methods even on matched distributions.
citing papers explorer
-
Class-frequency Guided Noise Schedule for Diffusion Models
Proposes CFRG noise schedule for diffusion models that assigns larger noises to low-frequency classes to improve generation on imbalanced datasets.
-
Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
Loss reweighting is cast as an inverse problem that dynamically infers class weights to equalize per-class average losses under the Neural Collapse simplex ETF target.
-
Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
DeCon decouples LTSSL into head-class and tail-class branches that interact and converge, delivering SOTA accuracy on mismatched-distribution benchmarks and outperforming prior methods even on matched distributions.