SOURCE-LINKED INTELLIGENCE

Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which for K > 1 lies away from all modes. We attribute this failure to pairwise contradictions--samples with nearly identical inputs but distant outputs--and propose Difference-Quotient Clustering (DQC), which partitions data to minimize intra-cluster output-vs-input discrepancy. Each sample is assigned to the cluster that minimizes its maximum contradiction ratio; a logits generator and a conditional network are then trained on the resulting labels.

Read original source ↗ Open in workspace

recordType

paper

region

Global