SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models

• URL: http://arxiv.org/abs/2503.08253v1
• Date: Tue, 11 Mar 2025 10:17:32 GMT
• Title: SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models
• Authors: Hesen Chen, Junyan Wang, Zhiyu Tan, Hao Li,
• Abstract summary: We introduce SARA, a hierarchical alignment framework that enforces multi-level representation constraints.<n>Experiments on ImageNet-256 show that SARA achieves an FID of 1.36 while converging twice as fast as REPA, surpassing recent state-of-the-art image generation methods.
• Score: 12.26595705520937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern diffusion models encounter a fundamental trade-off between training efficiency and generation quality. While existing representation alignment methods, such as REPA, accelerate convergence through patch-wise alignment, they often fail to capture structural relationships within visual representations and ensure global distribution consistency between pretrained encoders and denoising networks. To address these limitations, we introduce SARA, a hierarchical alignment framework that enforces multi-level representation constraints: (1) patch-wise alignment to preserve local semantic details, (2) autocorrelation matrix alignment to maintain structural consistency within representations, and (3) adversarial distribution alignment to mitigate global representation discrepancies. Unlike previous approaches, SARA explicitly models both intra-representation correlations via self-similarity matrices and inter-distribution coherence via adversarial alignment, enabling comprehensive alignment across local and global scales. Experiments on ImageNet-256 show that SARA achieves an FID of 1.36 while converging twice as fast as REPA, surpassing recent state-of-the-art image generation methods. This work establishes a systematic paradigm for optimizing diffusion training through hierarchical representation alignment.

Related papers

• Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID [82.12123628480371]
  Unsupervised person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning. Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning. We propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up objective for specific fine-grained patterns emphasized by each modality.
  arXiv  Detail & Related papers  (2025-04-27T13:58:12Z)
• Cross Paradigm Representation and Alignment Transformer for Image Deraining [40.66823807648992]
  We propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer) Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms to aid image reconstruction. We use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA)
  arXiv  Detail & Related papers  (2025-04-23T06:44:46Z)
• RAU: Towards Regularized Alignment and Uniformity for Representation Learning in Recommendation [7.193305599721105]
  We propose Regularized Alignment and Uniformity (RAU) to cope with sparse alignment and uneven uniformity issues. RAU consists of two novel regularization methods for alignment and uniformity to learn better user/item representation.
  arXiv  Detail & Related papers  (2025-03-24T03:03:21Z)
• Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence [83.15764564701706]
  We propose a novel framework that performs distributional vision-language alignment by integrating Cauchy-Schwarz divergence with mutual information.<n>In the proposed framework, we find that the CS divergence and mutual information serve complementary roles in multimodal alignment, capturing both the global distribution information of each modality and the pairwise semantic relationships.<n> Experiments on text-to-image generation and cross-modality retrieval tasks demonstrate the effectiveness of our method on vision-language alignment.
  arXiv  Detail & Related papers  (2025-02-24T10:29:15Z)
• Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport [24.141959555741696]
  Unsupervised cross-domain image retrieval aims to retrieve images sharing the same category across diverse domains without relying on labeled data.<n>Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment.<n>This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR.
  arXiv  Detail & Related papers  (2024-02-28T15:31:45Z)
• Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows [6.064702468344376]
  We propose a novel framework for analyzing the dynamics of distribution shift in real-world systems. We show that our approach captures well-documented forms of distribution shifts like polarization and disparate impacts that simpler models cannot capture.
  arXiv  Detail & Related papers  (2023-07-03T17:18:50Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
  Current adversarial adaptation methods attempt to align the cross-domain features. Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
  arXiv  Detail & Related papers  (2020-02-06T22:58:20Z)

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.