Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

• URL: http://arxiv.org/abs/2606.09718v1
• Date: Mon, 08 Jun 2026 16:44:18 GMT
• Title: Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
• Abstract summary: We introduce a framework for evaluating the representation and generation capabilities of diffusion models.<n>We analyze both discriminative and generative behavior of diffusion models.<n>Our results show that diffusion models can be monitored from a self-supervised perspective.
• Score: 35.85907484884706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for jointly evaluating the representation and generation capabilities of diffusion models. Specifically, we decompose features into invariant and residual components and derive the Invariant Contamination Ratio (ICR), a Fisher-based metric that quantifies how residual variation contaminates invariant signal in feature space. We use this framework to analyze both discriminative and generative behavior of diffusion models. On the representation side, we find that invariance peaks at intermediate noise levels, which also yield the best downstream classification performance. On the generative side, we study how training transitions from genuine generalization to memorization in data-limited regimes, and show that ICR serves as a sensitive training-time indicator of early learning: increasing residual energy along Fisher directions marks the onset of memorization, detectable from training features alone without external evaluators or held-out test sets. Overall, our results show that diffusion models can be monitored from a self-supervised perspective through the geometry of their learned representations.

Related papers

• Disentangled Representation Learning via Flow Matching [48.12507436294143]
  Disentangled representation learning aims to capture the underlying explanatory factors of observed data.<n>Existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment.<n>We propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space.
  arXiv  Detail & Related papers  (2026-02-05T02:14:36Z)
• Generalization of Diffusion Models Arises with a Balanced Representation Space [32.68561555837436]
  We analyze the distinctions between memorization and generalization in diffusion models through the lens of representation learning.<n>We show that memorization corresponds to the model storing raw training samples in the learned weights for encoding and decoding, yielding localized "spiky" representations.<n>We propose a representation-based method for detecting memorization and a training-free editing technique that allows precise control via representation steering.
  arXiv  Detail & Related papers  (2025-12-24T05:40:40Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning [38.869433924831156]
  iTimER is a self-supervised framework for ISTS representation learning.<n>It transforms unobserved timestamps into noise-aware training targets, enabling meaningful reconstruction signals.<n>iTimER consistently outperforms state-of-the-art methods under the ISTS setting.
  arXiv  Detail & Related papers  (2025-11-10T08:53:10Z)
• Learning Robust Diffusion Models from Imprecise Supervision [75.53546939251146]
  DMIS is a unified framework for training robust Conditional Diffusion Models from Imprecise Supervision.<n>Our framework is derived from likelihood and decomposes the objective into generative and classification components.<n>Experiments on diverse forms of imprecise supervision, covering tasks covering image generation, weakly supervised learning, and dataset condensation demonstrate that DMIS consistently produces high-quality and class-discriminative samples.
  arXiv  Detail & Related papers  (2025-10-03T14:00:32Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors [56.82596340418697]
  We propose a simple yet effective framework comprising a pre-trained Stable Diffusion (SD) model containing rich generative priors, a unified head (U-head) capable of integrating hierarchical representations, and an adapted expert providing discriminative priors. Comprehensive investigations unveil potential characteristics of Vermouth, such as varying granularity of perception concealed in latent variables at distinct time steps and various U-net stages. The promising results demonstrate the potential of diffusion models as formidable learners, establishing their significance in furnishing informative and robust visual representations.
  arXiv  Detail & Related papers  (2024-01-29T10:36:57Z)
• Learning Disentangled Discrete Representations [22.5004558029479]
  We show the relationship between discrete latent spaces and disentangled representations by replacing the standard Gaussian variational autoencoder with a tailored categorical variational autoencoder. We provide both analytical and empirical findings that demonstrate the advantages of discrete VAEs for learning disentangled representations.
  arXiv  Detail & Related papers  (2023-07-26T12:29:58Z)
• Manifold Contrastive Learning with Variational Lie Group Operators [5.0741409008225755]
  We propose a contrastive learning approach that directly models the latent manifold using Lie group operators parameterized by coefficients with a sparsity-promoting prior. A variational distribution over these coefficients provides a generative model of the manifold, with samples which provide feature augmentations applicable both during contrastive training and downstream tasks.
  arXiv  Detail & Related papers  (2023-06-23T15:07:01Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.