Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter counts-limits their application in real-world scenarios. Existing knowledge distillation methods in image restoration typically employ lightweight student models that directly mimic the intermediate features and reconstruction results of the teacher, overlooking the implicit attention relationships between them. To address this, we propose a Soft Knowledge Distillation (SKD) strategy that incorporates a Multi-dimensional Cross-net Attention (MCA) mechanism for compressing image restoration models. This mechanism facilitates interaction between the student and teacher across both channel and spatial dimensions, enabling the student to implicitly learn the attention matrices. Additionally, we employ a Gaussian kernel function to measure the distance between student and teacher features in kernel space, ensuring stable and efficient feature learning. To further enhance the quality of reconstructed images, we replace the commonly used L1 or KL divergence loss with a contrastive learning loss at the image level. Experiments on three tasks-image deraining, deblurring, and denoising-demonstrate that our SKD strategy significantly reduces computational complexity while maintaining strong image restoration capabilities.
Distribution-aware Dataset Distillation for Efficient Image Restoration
Sun Yat‑sen University（中山大学）；Fuzhou University（福州大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University of Science and Technology（南京理工大学）
Microsoft Research（微软研究院）；Sony Electronics Inc（索尼电子公司）；Purdue University at West Lafayette（普渡大学西拉法叶分校）
The inherent noise in the observed (e.g., scanned) binary document image degrades the image quality and harms the compression ratio through breaking the pattern repentance and adding entropy to the document images. In this paper, we design a cost function in Bayesian framework with dictionary learning. Minimizing our cost function produces a restored image which has better quality than that of the observed noisy image, and a dictionary for representing and encoding the image. After the restoration, we use this dictionary (from the same cost function) to encode the restored image following the …
Small compression noises, despite being transparent to human eyes, can adversely affect the results of many image restoration processes, if left unaccounted for. Especially, compression noises are highly detrimental to inverse operators of high-boosting (sharpening) nature, such as deblurring and superresolution against a convolution kernel. By incorporating the non-linear DCT quantization mechanism into the formulation for image restoration, we propose a new sparsity-based convex programming approach for joint compression noise removal and image restoration. Experimental results demonstrate s…
Transform image processing methods are methods that work in domains of image transforms, such as Discrete Fourier, Discrete Cosine, Wavelet and alike. They are the basic tool in image compression, in image restoration, in image re-sampling and geometrical transformations and can be traced back to early 1970-ths. The paper presents a review of these methods with emphasis on their comparison and relationships, from the very first steps of transform image compression methods to adaptive and local adaptive transform domain filters for image restoration, to methods of precise image re-sampling and …
Seoul National University（首尔国立大学）；NALBI Inc.（NALBI公司）
In this paper, we propose a method to solve the image restoration problem, which tries to restore the details of a corrupted image, especially due to the loss caused by JPEG compression. We have treated an image in the frequency domain to explicitly restore the frequency components lost during image compression. In doing so, the distribution in the frequency domain is learned using the cross entropy loss. Unlike recent approaches, we have reconstructed the details of an image without using the scheme of adversarial training. Rather, the image restoration problem is treated as a classification …
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks with compact models at various stages in the MRI workflow can significantly reduce the required storage space and provide considerable speedup. In computer vision, knowledge distillation is a commonly used method for model compression. In our work, we propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow in order to…
Tokyo Institute of Technology（东京工业大学）；Kadinche Corporation（Kadinche公司）；National Institute of Advanced Industrial Science and Technology（国立先进工业科学技术研究所）
Image restoration from a single image degradation type, such as blurring, hazing, random noise, and compression has been investigated for decades. However, image degradations in practice are often a mixture of several types of degradation. Such compositional degradations complicate restoration because they require the differentiation of different degradation types and levels. In this paper, we propose a convolutional neural network (CNN) model for estimating the degradation properties of a given degraded image. Furthermore, we introduce an image restoration CNN model that adopts the estimated …
Flordia International University（佛罗里达国际大学）；Northeastern University（东北大学）
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning parameters like compression rate, to blindly reduce image features, thereby lacking guarantee on both defense efficiency (i.e. accuracy of polluted images) and classification accuracy of benign images, after applying defense methods. To overcome these limitations, we propose a JPEG-based defensive compression framework, namely "feature distillation", to effectiv…
University of Würzburg（维尔茨堡大学）；MegaStudyEdu（MegaStudy教育）
Compression plays an important role on the efficient transmission and storage of images and videos through band-limited systems such as streaming services, virtual reality or videogames. However, compression unavoidably leads to artifacts and the loss of the original information, which may severely degrade the visual quality. For these reasons, quality enhancement of compressed images has become a popular research topic. While most state-of-the-art image restoration methods are based on convolutional neural networks, other transformers-based methods such as SwinIR, show impressive performance …
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；University of Rochester（罗切斯特大学）
An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their corresponding pristine-quality images. However, pristine-quality images are usually unavailable in blind image restoration tasks and real-world scenarios. In this paper, we propose a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references. Specifically, we extract reference information from degraded images by dist…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this paper, we present a new approach suitable for handling the image-specific and spatially-varying nature of degradation in images affected by practically occurring artifacts such as blur, rain-streaks. We decompose the restoration task into two stages of degradation localization and degraded region-guided restoration, unlike existing methods which directly learn a …
University of Chinese Academy of Sciences（中国科学院大学）；Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences（中国科学院虚拟经济与数据科学研究中心）；Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences（中国科学院大数据挖掘与知识管理重点实验室）
In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concatenated attention neural network (CANet) is specifically designed for image restoration. The main contributions of this paper are as follows: First, by applying concise but effective concatenation and feature selection mechanism, we establish a novel connection mechanism which connect different modules in the modules stacking network. Second, both pixel-wise and channel-wise attention mechanisms are used in each module …
Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）；Alibaba Group（阿里巴巴集团）
With the spread of tampered images, locating the tampered regions in digital images has drawn increasing attention. The existing image tampering localization methods, however, suffer from severe performance degradation when the tampered images are subjected to some post-processing, as the tampering traces would be distorted by the post-processing operations. The poor robustness against post-processing has become a bottleneck for the practical applications of image tampering localization techniques. In order to address this issue, this paper proposes a novel restoration-assisted framework for i…
UIUC（伊利诺伊大学厄巴纳-香槟分校）；Northeastern University（东北大学）；Google Brain（谷歌大脑）；ByteDance AI Lab（字节跳动人工智能实验室）；University of Oregon（俄勒冈大学）
Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network based methods for image restoration do not take full advantage of self-similarities by relying on self-attention neural modules that only process information at the same scale. To solve this problem, we present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid. Inspired by the fact …
This paper investigates a fully unsupervised statistical method for edge preserving image restoration and compression using a spatial decomposition scheme. Smoothed maximum likelihood is used for local estimation of edge pixels from mixture parametric models of local templates. For the complementary smooth part the traditional L2-variational problem is solved in the Fourier domain with Thin Plate Spline (TPS) regularization. It is well known that naive Fourier compression of the whole image fails to restore a piece-wise smooth noisy image satisfactorily due to Gibbs phenomenon. Images are inte…
Hierarchical Semantic Compression for Consistent Image Semantic Restoration
School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Electronic and Information Engineering, University of Electronic Science and Technology of China（电子科技大学电子信息工程学院）
We present 14 autoencoders, 15 kernels and 14 multilayer perceptrons for electron micrograph restoration and compression. These have been trained for transmission electron microscopy (TEM), scanning transmission electron microscopy (STEM) and for both (TEM+STEM). TEM autoencoders have been trained for 1$\times$, 4$\times$, 16$\times$ and 64$\times$ compression, STEM autoencoders for 1$\times$, 4$\times$ and 16$\times$ compression and TEM+STEM autoencoders for 1$\times$, 2$\times$, 4$\times$, 8$\times$, 16$\times$, 32$\times$ and 64$\times$ compression. Kernels and multilayer perceptrons have b…
Recent applications pose requirements of both cross-domain knowledge transfer and model compression to machine learning models due to insufficient training data and limited computational resources. In this paper, we propose a new knowledge distillation model, named Spirit Distillation (SD), which is a model compression method with multi-domain knowledge transfer. The compact student network mimics out a representation equivalent to the front part of the teacher network, through which the general knowledge can be transferred from the source domain (teacher) to the target domain (student). To fu…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training b…
This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns unique representations from the data distribution due to its distinct architecture. This helps the ensemble generalize better by combining every model's knowledge. The distilled students and ensemble teacher are trained simultaneously without requiring any pretrained weights. Moreover, our proposed method can deliver multi-compressed students with s…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. We are inspired by that the neural codec is a natural denoiser. In neural codec, the noisy and uncorrelated contents which are hard to predict but cost lots of bits are more inclined to be discarded for bitrate saving. Therefore, we design a neural compressi…
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an awesome ''performance maker'', knowledge distillation is demonstrated to be particularly efficacious in exploring low-priced GANs. In this paper, we investigate the irreplaceability of teacher discriminator and present an inventive discriminator-cooperated distillation, abbreviated as DCD, towards refining better feature maps from the generator. In contrast to conventional pixel-to-pixel match methods in feature map di…
Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an alternative strategy where multiple simple student networks benefit from sharing knowledge, even in the absence of a powerful but static teacher network. Motivated by these findings, we propose a single-teacher, multi-student framework that leverages both KD and ML to achieve better performance. Furthermore, an online distillation strategy is utilized to train the te…
In this paper we propose a deep residual autoencoder exploiting Residual-in-Residual Dense Blocks (RRDB) to remove artifacts in JPEG compressed images that is independent from the Quality Factor (QF) used. The proposed approach leverages both the learning capacity of deep residual networks and prior knowledge of the JPEG compression pipeline. The proposed model operates in the YCbCr color space and performs JPEG artifact restoration in two phases using two different autoencoders: the first one restores the luma channel exploiting 2D convolutions; the second one, using the restored luma channel…
Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images, however, they are burdensome to deploy on resource-constrained devices due to ponderous computational costs and hulking memory usage. Although recent efforts on compressing GANs have acquired remarkable results, they still exist potential model redundancies and can be further compressed. To solve this issue, we propose a novel online multi-granularity distillation (OMGD) scheme to obtain lightweight GANs, which contributes to generating high-fidelity images with low computational demands. W…
Ocean University of China（中国海洋大学）；Technical University of Munich（慕尼黑工业大学）；Virginia Commonwealth University（弗吉尼亚联邦大学）；University of Leicester（莱斯特大学）；University of Portsmouth（朴茨茅斯大学）
Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation methods need to access the original training data, which usually has a huge size and is often unavailable. To tackle this problem, we propose a novel data-free approach in this paper, named Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. To be specific, we use a generator to create samples through dual disc…
Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we propose Dream Distillation, a data-independent model compression framework. Our experiments show that Dream Distillation can achieve 88.5% accuracy on the CIFAR-10 test set without actually training on the original data!
