Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

• URL: http://arxiv.org/abs/2410.06719v3
• Date: Fri, 18 Oct 2024 06:39:27 GMT
• Title: Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
• Authors: Benyuan Meng, Qianqian Xu, Zitai Wang, Zhiyong Yang, Xiaochun Cao, Qingming Huang,
• Abstract summary: We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. We propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology.
• Score: 119.02857688205295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://github.com/Darkbblue/diffusion-content-shift.

Related papers

• $\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models [10.68914376295842]
  We study $textithow$ rich visual semantic information is represented within various layers and denoising timesteps of different diffusion architectures. We uncover monosemantic interpretable features by leveraging k-sparse autoencoders (k-SAE) We substantiate our mechanistic interpretations via transfer learning using light-weight classifiers on off-the-shelf diffusion models' features.
  arXiv  Detail & Related papers  (2024-11-23T03:54:22Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models [82.8261101680427]
  Smooth latent spaces ensure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image inversion, inversion, and editing. We propose Smooth Diffusion, a new category of diffusion models that can be simultaneously high-performing and smooth.
  arXiv  Detail & Related papers  (2023-12-07T16:26:23Z)
• Eliminating Lipschitz Singularities in Diffusion Models [51.806899946775076]
  We show that diffusion models frequently exhibit the infinite Lipschitz near the zero point of timesteps. This poses a threat to the stability and accuracy of the diffusion process, which relies on integral operations. We propose a novel approach, dubbed E-TSDM, which eliminates the Lipschitz of the diffusion model near zero.
  arXiv  Detail & Related papers  (2023-06-20T03:05:28Z)
• InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models [35.566528358691336]
  InfoDiffusion is an algorithm that augments diffusion models with low-dimensional latent variables. InfoDiffusion relies on a learning objective regularized with the mutual information between observed and hidden variables. We find that InfoDiffusion learns disentangled and human-interpretable latent representations that are competitive with state-of-the-art generative and contrastive methods.
  arXiv  Detail & Related papers  (2023-06-14T21:48:38Z)
• Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation [11.80682025950519]
  In this work, we investigate the diffusion (physics) in diffusion (machine learning) properties. We propose our Cyclic One-Way Diffusion (COW) method to control the direction of diffusion phenomenon. Our method provides a novel perspective to understand the task needs and is applicable to a wider range of customization scenarios.
  arXiv  Detail & Related papers  (2023-06-14T05:25:06Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• Diffusion-GAN: Training GANs with Diffusion [135.24433011977874]
  Generative adversarial networks (GANs) are challenging to train stably. We propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate instance noise. We show that Diffusion-GAN can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.
  arXiv  Detail & Related papers  (2022-06-05T20:45:01Z)

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.