Existing reference (RF)-based super-resolution (SR) models try to improve perceptual quality in SR under the assumption of the availability of high-resolution RF images paired with low-resolution (LR) inputs at testing. As the RF images should be similar in terms of content, colors, contrast, etc. to the test image, this hinders the applicability in a real scenario. Other approaches to increase the perceptual quality of images, including perceptual loss and adversarial losses, tend to dramatically decrease fidelity to the ground-truth through significant decreases in PSNR/SSIM. Addressing both issues, we propose a simple yet universal approach to improve the perceptual quality of the HR prediction from a pre-trained SR network on a given LR input by further fine-tuning the SR network on a subset of images from the training dataset with similar patterns of activation as the initial HR prediction, with respect to the filters of a feature extractor. In particular, we show the effects of fine-tuning on these images in terms of the perceptual quality and PSNR/SSIM values. Contrary to perceptually driven approaches, we demonstrate that the fine-tuned network produces a HR prediction with both greater perceptual quality and minimal changes to the PSNR/SSIM with respect to the initial HR prediction. Further, we present novel numerical experiments concerning the filters of SR networks, where we show through filter correlation, that the filters of the fine-tuned network from our method are closer to "ideal" filters, than those of the baseline network or a network fine-tuned on random images.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；The Chinese University of Hong Kong（香港中文大学）
Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp to train networks on interpolations of sample pairs, which enc…
DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；Guangdong Power Grid, Ltd.（广东电网有限公司）；School of Computer Science, Sun Yat-sen University（中山大学计算机学院）
EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training
Christian Doppler Laboratory ATHENA（Christian Doppler实验室ATHENA）；Alpen-Adria-Universität Klagenfurt（阿尔卑斯-亚德里亚大学克雷格福特）；College of Information and Communication Engineering（信息与通信工程学院）
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend to overfit to the degradation seen during training. We present an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduce a conditional learning perspective that extends to both super-resolution and denoising. Building on our formulation, we propose a stochastic frequency masking of images used in…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
We mainly analyze and solve the overfitting problem of deep image prior (DIP). Deep image prior can solve inverse problems such as super-resolution, inpainting and denoising. The main advantage of DIP over other deep learning approaches is that it does not need access to a large dataset. However, due to the large number of parameters of the neural network and noisy data, DIP overfits to the noise in the image as the number of iterations grows. In the thesis, we use hybrid deep image priors to avoid overfitting. The hybrid priors are to combine DIP with an explicit prior such as total variation…
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
Robotics Institute, Athena Research and Innovation Center（雅典娜研究与创新中心机器人研究所）；School of Electrical and Computer Engineering, National Technical University of Athens（雅典国家技术大学电气与计算机工程学院）
Tampere University（坦佩雷大学）；Nokia Technologies（诺基亚技术公司）
In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference time, the encoder or the latent tensor output by the encoder can be optimized for each test image. This optimization can be regarded as a form of adaptation or benevolent overfitting to the input content. In order to reduce the gap between training and inference conditions, we propose a new training paradigm for learned image compression, which is based on meta-…
Nokia Technologies（诺基亚技术公司）；Tampere University（坦佩雷大学）
Neural image coding represents now the state-of-the-art image compression approach. However, a lot of work is still to be done in the video domain. In this work, we propose an end-to-end learned video codec that introduces several architectural novelties as well as training novelties, revolving around the concepts of adaptation and attention. Our codec is organized as an intra-frame codec paired with an inter-frame codec. As one architectural novelty, we propose to train the inter-frame codec model to adapt the motion estimation process based on the resolution of the input video. A second arch…
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Shanghai Key Laboratory of Digital Media Processing and Transmission（上海市数字媒体处理与传输重点实验室）
By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial learning. As an enhancement, category alignment is involved during adaptation to reinforce target feature discrimination by utilizing model prediction. However, there remain unexplored problems about pseudo-label inaccuracy incurred by wrong category predictions on target domain, and distribution deviation caused by overfitting on source domain. In this paper, w…
ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation
The JC STEM Lab of Machine Learning and Computer Vision（机器学习与计算机视觉的JC STEM实验室）；Department of Electrical and Electronic Engineering（电气与电子工程系）；The Hong Kong Polytechnic University（香港理工大学）；Department of Computer Science and Engineering（计算机科学与工程系）；The Chinese University of Hong Kong（香港中文大学）
Low-Cost Test-Time Adaptation for Robust Video Editing
UESTC（电子科技大学）；USTC（中国科学技术大学）；University of Minnesota–Twin Cities（明尼苏达大学-双城分校）；Emory University（埃默里大学）；Nanjing University（南京大学）；Lanzhou University（兰州大学）；Ohio State University, Columbus（俄亥俄州立大学-哥伦布分校）；Chinese Academy of Sciences（中国科学院）；Peking University（北京大学）
Tsinghua University（清华大学）；University of Science and Technology Beijing（北京科技大学）
Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. However, to our knowledge, few-shot image generation tasks have yet to be studied with DDPM-based approaches. Modern approaches are mainly built on Generative Adversarial Networks (GANs) and adapt models pre-trained on large source domains to target domains using a few available samples. In this paper, we make the first attempt to study when do DDPMs overfit and suffer severe diversity degradation as training data become …
Rutgers University（罗格斯大学）；Amazon Web Services（亚马逊云科技）
Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging test-time adaptation (TTA) problem, where a model adapts to the target domain without accessing the source data. We propose a simple recipe called \textit{Data-efficient Prompt Tuning} (DePT) with two key ingredients. First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation. We find such parameter-efficient …
Computer Vision Laboratory, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机视觉实验室）；Dept. of Electrical Engineering ESAT, KU Leuven, Belgium（比利时鲁汶大学电气与信息工程系（ESAT））
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this task. However, a segmentation algorithm generalizing to various scenes and conditions would require an enormously diverse dataset, making the labour intensive data acquisition and labeling process prohibitively expensive. Under the assumption of structural similarities between segmentation maps, domain adaptation promises to resolve this challenge by transferr…
In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific data and the high computational cost of full model adaptation. In this paper, we introduce Lite-Diff (Lightweight Diffusion Model Adaptation), a novel finetuning approach that integrates lightweight adaptation layers into a frozen diffusion U-Net while enhancing training with a latent morphological autoencoder (for domain-specific latent consistency) and a p…
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random "dropout" gives bi…
Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the learned model to real world scenarios. This is mainly due to two reasons: 1) the model overfits to synthetic images, making the convolutional filters incompetent to extract informative representation for real images; 2) there is a distribution difference between synthetic and real data, which is also known as the domain adaptation problem. To this end, we prop…
National University of Singapore（新加坡国立大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data is highly insufficient, making most existing domain adaptation methods ineffective. Second, object detection involves simultaneous localization and classification, further complicating the model adaptation process. Third, the model suffers from over-adaptation (similar to overfitting when training wi…
Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In this paper we overcome such limitations by presenting the first methodology for domain adaption of such a class of trackers. To reduce the labeling effort we propose a weakly-supervised adaptation strategy, in which reinforcement learning is used to express weak supervision as a scalar application-dependent and temporally-delayed feedback. At the same time, kno…
Department of Computer Science, University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校计算机科学系）
This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learn…
We present a new method for one shot domain adaptation. The input to our method is trained GAN that can produce images in domain A and a single reference image I_B from domain B. The proposed algorithm can translate any output of the trained GAN from domain A to domain B. There are two main advantages of our method compared to the current state of the art: First, our solution achieves higher visual quality, e.g. by noticeably reducing overfitting. Second, our solution allows for more degrees of freedom to control the domain gap, i.e. what aspects of image I_B are used to define the domain B. T…
Deep learning image reconstruction algorithms often suffer from model mismatches when the acquisition scheme differs significantly from the forward model used during training. We introduce a Generalized Stein's Unbiased Risk Estimate (GSURE) loss metric to adapt the network to the measured k-space data and minimize model misfit impact. Unlike current methods that rely on the mean square error in kspace, the proposed metric accounts for noise in the measurements. This makes the approach less vulnerable to overfitting, thus offering improved reconstruction quality compared to schemes that rely o…
Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）；Mila, University of Montreal（蒙特利尔大学Mila研究所）；Inception Institute of Artificial Intelligence（Inception人工智能研究所）；University of Electronic Science and Technology of China（电子科技大学）；Singapore Eye Research Institute（新加坡眼科研究所）
Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images, due to various domain discrepancy between the training images (source domain) and the test images (target domain), which raises a domain adaptation issue. In clinical settings, it is difficult to collect enough annotated target domain data in a short period. Few-shot domain adaptation, i.e., adapting a trained model with a handful of annotations, is highly practical and useful in this case. In this paper, we propose a Polymorphic Transformer (Polyformer), which can b…
Enhancing Test Time Adaptation with Few-shot Guidance
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（图像通信与网络工程研究所，上海交通大学）；State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；School of Software & Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University（软件学院及SDU-NTU联合人工智能研究中心，山东大学）；Macao Polytechnic University（澳门理工学院）
National University of Singapore（新加坡国立大学）；Xiamen University（厦门大学）；University of Trento（特伦托大学）
In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation. SF-OCDA is more challenging than the traditional domain adaptation but it is more practical. It jointly considers (1) the issues of data privacy and data storage and (2) the scenario of multiple target domains and unseen open domains. In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. The model is evaluated on the samples from the target and unseen open domains. To solve this problem, we present an …
Contrastive self-supervised learning methods learn to map data points such as images into non-parametric representation space without requiring labels. While highly successful, current methods require a large amount of data in the training phase. In situations where the target training set is limited in size, generalization is known to be poor. Pretraining on a large source data set and fine-tuning on the target samples is prone to overfitting in the few-shot regime, where only a small number of target samples are available. Motivated by this, we propose a domain adaption method for self-super…
Shenzhen University（深圳大学）；IBM（国际商业机器公司）；University of Nottingham（诺丁汉大学）
Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data. However, adversarial training could overfit to a specific type of adversarial attack and also lead to standard accuracy drop on clean images. To this end, we propose a novel Class-Aware Domain Adaptation…
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）前沿人工智能研究中心（CFAR））；Institute for Infocomm Research (IR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）资讯通信研究院（IR））
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
There are many recent research efforts to fine-tune a pre-trained generator with a few target images to generate images of a novel domain. Unfortunately, these methods often suffer from overfitting or under-fitting when fine-tuned with a single target image. To address this, here we present a novel single-shot GAN adaptation method through unified CLIP space manipulations. Specifically, our model employs a two-step training strategy: reference image search in the source generator using a CLIP-guided latent optimization, followed by generator fine-tuning with a novel loss function that imposes …
Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data. Nevertheless, most active learning methods are not inherently designed to handle domain gap between data distribution, on the other hand, some active domain adaptation methods (ADA) usually requires complicated query functions, which is vulnerable to overfitting. In …
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）
It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to classify unlabeled target images using source labeled images. Unfortunately, deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT). However OT can cause negative transfer, i.e. aligning samples with…
Data-efficient domain adaptation with only a few labelled data is desired for many robotic applications, e.g., in grasping detection, the inference skill learned from a grasping dataset is not universal enough to directly apply on various other daily/industrial applications. This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning, where these two components deeply interact with each other. The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism…
