Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

• URL: http://arxiv.org/abs/2505.18584v1
• Date: Sat, 24 May 2025 08:20:36 GMT
• Title: Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
• Authors: Chaofan Gan, Yuanpeng Tu, Xi Chen, Tieyuan Chen, Yuxi Li, Mehrtash Harandi, Weiyao Lin,
• Abstract summary: Diffusion Transformers (DiTs) exhibit a critical phenomenon in which very few feature activations exhibit significantly larger values than others.<n>We propose Diffusion Transformer Feature (DiTF), a training-free framework designed to extract semantic-discriminative features from DiTs.
• Score: 39.83216506924748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for accurate dense correspondence. Distinct from SD, DiTs exhibit a critical phenomenon in which very few feature activations exhibit significantly larger values than others, known as \textit{massive activations}, leading to uninformative representations and significant performance degradation for DiTs. The massive activations consistently concentrate at very few fixed dimensions across all image patch tokens, holding little local information. We trace these dimension-concentrated massive activations and find that such concentration can be effectively localized by the zero-initialized Adaptive Layer Norm (AdaLN-zero). Building on these findings, we propose Diffusion Transformer Feature (DiTF), a training-free framework designed to extract semantic-discriminative features from DiTs. Specifically, DiTF employs AdaLN to adaptively localize and normalize massive activations with channel-wise modulation. In addition, we develop a channel discard strategy to further eliminate the negative impacts from massive activations. Experimental results demonstrate that our DiTF outperforms both DINO and SD-based models and establishes a new state-of-the-art performance for DiTs in different visual correspondence tasks (\eg, with +9.4\% on Spair-71k and +4.4\% on AP-10K-C.S.).

Related papers

• TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation [34.73820805875123]
  TIDE (Temporal-aware Sparse Autoencoders for Interpretable Diffusion transformErs) is a novel framework that enhances temporal reconstruction within DiT activation layers across denoising steps.<n>TIDE employs Sparse Autoencoders (SAEs) with a sparse bottleneck layer to extract interpretable and hierarchical features.<n>Our approach achieves state-of-the-art reconstruction performance, with a mean squared error (MSE) of 1e-3 and a cosine similarity of 0.97.
  arXiv  Detail & Related papers  (2025-03-10T08:35:51Z)
• PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity [9.092404060771306]
  Diffusion models have shown impressive results in generating high-quality conditional samples.<n>However, existing methods often require additional training or neural function evaluations (NFEs)<n>We propose a novel and efficient method, termed PLADIS, which boosts pre-trained models by leveraging sparse attention.
  arXiv  Detail & Related papers  (2025-03-10T07:23:19Z)
• Mixture of Hidden-Dimensions Transformer [50.40325486463241]
  We study hidden dimension sparsity and observe that trained Transformers utilize only a small fraction of token dimensions.<n>We propose MoHD (Mixture of Hidden Dimensions), a sparse conditional activation architecture.<n>It achieves 1.7% higher performance with 50% fewer activation parameters and 3.7% higher performance with a 3x parameter expansion at constant activation cost.
  arXiv  Detail & Related papers  (2024-12-07T13:15:22Z)
• Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features [115.33889811527533]
  Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks.
  arXiv  Detail & Related papers  (2024-10-04T16:05:14Z)
• DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing [5.174900115018253]
  We propose a data-free post-training quantization (PTQ) method for efficient Diffusion Transformers (DiTs) DiTAS relies on the proposed temporal-aggregated smoothing techniques to mitigate the impact of the channel-wise outliers within the input activations. We show that our approach enables 4-bit weight, 8-bit activation (W4A8) quantization for DiTs while maintaining comparable performance as the full-precision model.
  arXiv  Detail & Related papers  (2024-09-12T05:18:57Z)
• Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation [37.79819260918366]
  Continual Test-Time Adaptation (CTTA) aims to adapt the pre-trained model to ever-evolving target domains. We explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task.
  arXiv  Detail & Related papers  (2024-05-26T08:51:39Z)
• SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer [102.39050180060913]
  Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. Recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning. In this work, we address these limitations by novelly unleashing the self-supervised discrimination knowledge to boost DiT training.
  arXiv  Detail & Related papers  (2024-03-25T17:59:35Z)
• From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers [52.199303258423306]
  We propose a novel density loss that encourages higher activation sparsity in pre-trained models. Our proposed method, textbfDEFT, can consistently reduce activation density by up to textbf44.94% on RoBERTa$_mathrmLarge$ and by textbf53.19% (encoder density) and textbf90.60% (decoder density) on Flan-T5$_mathrmXXL$.
  arXiv  Detail & Related papers  (2024-02-02T21:25:46Z)
• The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers [59.87030906486969]
  This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. We show that sparsity is a prevalent phenomenon that occurs for both natural language processing and vision tasks. We discuss how sparsity immediately implies a way to significantly reduce the FLOP count and improve efficiency for Transformers.
  arXiv  Detail & Related papers  (2022-10-12T15:25:19Z)

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.