Background Gradients Shape Memorization in Flow Matching

arXiv:2609.33210 · cs.CV · Submitted 2026-09-27 · Read on arXiv

cs.CV

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: 38 pages, 8 figures, 34 tables

License: http://creativecommons.org/licenses/by/4.0/

The gist: Repetition is closely associated with memorization in generative models, but how other training images affect the retention and copying of targets remains unclear.

Terminology

Abstract

Repetition is closely associated with memorization in generative models, but how other training images affect the retention and copying of targets remains unclear. We study this question in class-conditioned flow matching, where images outside the target set form the background. At fixed target repetition and same-class background row count, replacing repeated same-class images with distinct images reduces the target extraction rate from 80.7% to 18.0%. To explain this effect, we develop a paired-trajectory framework that isolates target-induced parameter displacement and the background gradient response to it. This response has an exact path-integrated curvature representation, connecting background loss geometry to target learning. Reciprocal response transfer between repeated and distinct backgrounds changes target retention and copying in both directions, establishing the response's causal role. After target removal, the response correction parallel to the target-induced displacement preserves approximately 90% of the copying effects of full response transfer. Directly scaling the displacement also changes copying without further training. The post-removal copying effects of reciprocal transfer are reproduced across datasets and architectures. Together, these results identify the background gradient response as a mechanism through which same-class training data shape the retention of target learning and the reproduction of target images.

Sources

Related papers