Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
- URL: http://arxiv.org/abs/2501.09052v1
- Date: Wed, 15 Jan 2025 13:42:39 GMT
- Title: Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
- Authors: Shuang Cui, Yi Li, Jiangmeng Li, Xiongxin Tang, Bing Su, Fanjiang Xu, Hui Xiong,
- Abstract summary: Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one.
distribution shifts in defocused images generally lead to performance degradation of existing methods.
We propose a novel Siamese networks-based continual test-time adaptation framework.
- Score: 29.730411221998633
- License:
- Abstract: Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences. In this work, we gauge the intrinsic reason behind the performance degradation, which is identified as the heterogeneity of lens-specific point spread functions. Empirical evidence supports this finding, motivating us to employ a continual test-time adaptation (CTTA) paradigm for SIDD. However, traditional CTTA methods, which primarily rely on entropy minimization, cannot sufficiently explore task-dependent information for pixel-level regression tasks like SIDD. To address this issue, we propose a novel Siamese networks-based continual test-time adaptation framework, which adapts source models to continuously changing target domains only requiring unlabeled target data in an online manner. To further mitigate semantically erroneous textures introduced by source SIDD models under severe degradation, we revisit the learning paradigm through a structural causal model and propose Causal Siamese networks (CauSiam). Our method leverages large-scale pre-trained vision-language models to derive discriminative universal semantic priors and integrates these priors into Siamese networks, ensuring causal identifiability between blurry inputs and restored images. Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains.
Related papers
- Model Will Tell: Training Membership Inference for Diffusion Models [15.16244745642374]
Training Membership Inference (TMI) task aims to determine whether a specific sample has been used in the training process of a target model.
In this paper, we explore a novel perspective for the TMI task by leveraging the intrinsic generative priors within the diffusion model.
arXiv Detail & Related papers (2024-03-13T12:52:37Z) - Fiducial Focus Augmentation for Facial Landmark Detection [4.433764381081446]
We propose a novel image augmentation technique to enhance the model's understanding of facial structures.
We employ a Siamese architecture-based training mechanism with a Deep Canonical Correlation Analysis (DCCA)-based loss.
Our approach outperforms multiple state-of-the-art approaches across various benchmark datasets.
arXiv Detail & Related papers (2024-02-23T01:34:00Z) - Cross-Modality Perturbation Synergy Attack for Person Re-identification [66.48494594909123]
The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities.
Existing attack methods have primarily focused on the characteristics of the visible image modality.
This study proposes a universal perturbation attack specifically designed for cross-modality ReID.
arXiv Detail & Related papers (2024-01-18T15:56:23Z) - JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancement [69.6035373784027]
Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models.
Previous methods may neglect the importance of a sufficient formulation of task-specific condition strategy.
We propose JoReS-Diff, a novel approach that incorporates Retinex- and semantic-based priors as the additional pre-processing condition.
arXiv Detail & Related papers (2023-12-20T08:05:57Z) - DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection.
It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor.
Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2023-12-11T18:38:28Z) - Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations [61.132408427908175]
zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain.
With only a single representative text feature instead of real images, the synthesized images gradually lose diversity.
We propose a novel method to find semantic variations of the target text in the CLIP space.
arXiv Detail & Related papers (2023-08-21T08:12:28Z) - Diffusion Models for Image Restoration and Enhancement -- A
Comprehensive Survey [96.99328714941657]
We present a comprehensive review of recent diffusion model-based methods on image restoration.
We classify and emphasize the innovative designs using diffusion models for both IR and blind/real-world IR.
We propose five potential and challenging directions for the future research of diffusion model-based IR.
arXiv Detail & Related papers (2023-08-18T08:40:38Z) - Unsupervised Domain-Specific Deblurring using Scale-Specific Attention [0.25797036386508543]
We propose unsupervised domain-specific deblurring using a scale-adaptive attention module (SAAM)
Our network does not require supervised pairs for training, and the deblurring mechanism is primarily guided by adversarial loss.
Different ablation studies show that our coarse-to-fine mechanism outperforms end-to-end unsupervised models and SAAM is able to attend better compared to attention models used in literature.
arXiv Detail & Related papers (2021-12-12T07:47:45Z) - Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms.
Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
arXiv Detail & Related papers (2021-11-27T12:12:57Z) - MFIF-GAN: A New Generative Adversarial Network for Multi-Focus Image
Fusion [29.405149234582623]
Multi-Focus Image Fusion (MFIF) is a promising technique to obtain all-in-focus images.
One of the research trends of MFIF is to avoid the defocus spread effect (DSE) around the focus/defocus boundary (FDB)
We propose a network termed MFIF-GAN to generate focus maps in which the foreground region are correctly larger than the corresponding objects.
arXiv Detail & Related papers (2020-09-21T09:36:34Z)
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.