SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching

• URL: http://arxiv.org/abs/2608.01990v1
• Date: Mon, 03 Aug 2026 09:50:51 GMT
• Title: SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching
• Abstract summary: Regularizing internal representations has emerged as an effective accelerator, yet existing methods split into two families with complementary costs.<n>We propose Structural.<n>free Affinity Regularization (SPARE), a regularizer that matches the pairwise affinities of intermediate tokens to those of the clean latents.<n>On ImageNet $256 times 256$ with SiT backbones under matched 400K-iteration budgets, SPARE adds no encoder, head, or parameters and only 0.08 GB of training memory.
• Score: 30.43836162456455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Denoising diffusion transformers achieve strong generation quality but converge slowly during training. Regularizing their internal representations has emerged as an effective accelerator, yet existing methods split into two families with complementary costs. Target-based methods strengthen representations by aligning them to external features, which requires an external encoder and a learnable projection head to bridge feature spaces. Target-free methods hold no reference at all, and can only repel the model's own features across samples or layers, discarding whatever structure the data contains. Prior work suggests that spatial structure, rather than global semantics, drives the gains of alignment. We therefore ask whether such structure can serve as a target directly, and whether it exists not only within an image but across images. Our key insight is that the clean data latent already carries this structure in the relations among its tokens, where a relation is the similarity between two tokens, a single scalar comparable across feature spaces without a projection head. We propose Structural Parameter-free Affinity Regularization (SPARE), a regularizer that matches the pairwise affinities of intermediate tokens to those of the clean latents. To exploit this structure fully, SPARE extends the matching to token pairs across images, precisely the pairs that prior target-free methods repel by default, and calibrates both relation types with a single learning objective. On ImageNet $256 \times 256$ with SiT backbones under matched 400K-iteration budgets, SPARE adds no encoder, head, or parameters and only 0.08 GB of training memory, yet attains the lowest FID among parameter-free regularizers in every tested setting, recovers 37 to 54\% of REPA's FID reduction, and improves over REPA when combined with it, reaching FID 1.90 under classifier-free guidance at 1M iterations.

Related papers

• SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation [0.0]
  This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation.<n>We describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation.
  arXiv  Detail & Related papers  (2026-08-31T23:19:59Z)
• Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation [30.789763956644958]
  Cross-modal matching methods are largely restricted by their reliance on either matching labels or strictly aligned hardware.<n>We propose a novel two-stage training paradigm to address this problem.<n>Our proposed method achieves state-of-the-art performance on both MVSEC and TUM-VIE pose estimation tasks.
  arXiv  Detail & Related papers  (2026-07-11T02:23:11Z)
• AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens [39.0104982235623]
  We propose AdaTok, a self-budgeting discrete 1D tokenizer.<n>AdaTok combines Prioritized Representation Learning, which orders tokens with nested tail masking, with Adaptive Token Allocation.<n>On ImageNet-1K, AdaTok-Full reaches rFID 1.31 at 256 tokens, while AdaTok-Adaptive attains rFID 1.50 using only 118 tokens on average, outperforming discrete 1D baselines at comparable budgets.
  arXiv  Detail & Related papers  (2026-06-05T11:49:28Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring [9.25889614321249]
  Out-of-distribution (OOD) detection is essential for deploying deep learning models reliably, yet no single method performs consistently across architectures and datasets.<n>We propose CORE, which disentangles the two signals by scoring each subspace independently and combines them via normalized summation.<n> CORE achieves competitive or state-of-the-art performance across five architectures and five benchmark configurations.
  arXiv  Detail & Related papers  (2026-03-18T21:23:54Z)
• Learning Accurate Segmentation Purely from Self-Supervision [87.78965637247107]
  Selfment is a fully self-supervised framework that segments objects directly from raw images without human labels.<n>Selfment sets new state-of-the-art (SoTA) results across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-02-27T07:36:32Z)
• CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval [54.15776146365823]
  Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text.<n>We propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components.
  arXiv  Detail & Related papers  (2026-01-07T09:21:38Z)
• REAR: Rethinking Visual Autoregressive Models via Generator-Tokenizer Consistency Regularization [130.46612643194973]
  reAR is a simple training strategy introducing a token-wise regularization objective.<n>On ImageNet, it reduces gFID from 3.02 to 1.86 and improves IS to 316.9 using a standardization-based tokenizer.<n>When applied to advanced tokenizers, it achieves a gFID of 1.42 with only 177M parameters, matching the performance with larger state-of-the-art diffusion models (675M)
  arXiv  Detail & Related papers  (2025-10-06T02:48:13Z)
• Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model [69.79418000132995]
  AliTok is a novel Aligned Tokenizer that alters the dependency structure of the token sequence.<n>Building upon AliTok, a standard decoder-only autoregressive model with just 177M parameters achieves a gFID of 1.44 and an IS of 319.5 on the ImageNet-256 benchmark.
  arXiv  Detail & Related papers  (2025-06-05T17:45:10Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection [0.0]
  Reconstruction autoencoder-based methods deal with the problem by using input reconstruction error as a metric of novelty vs. normality. We introduce semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods. Our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.
  arXiv  Detail & Related papers  (2022-03-04T09:04:55Z)

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.