Vision Transformers (ViTs) enabled the use of the transformer architecture on vision tasks showing impressive performances when trained on big datasets. However, on relatively small datasets, ViTs are less accurate given their lack of inductive bias. To this end, we propose a simple but still effective Self-Supervised Learning (SSL) strategy to train ViTs, that without any external annotation or external data, can significantly improve the results. Specifically, we define a set of SSL tasks based on relations of image patches that the model has to solve before or jointly the supervised task. Differently from ViT, our RelViT model optimizes all the output tokens of the transformer encoder that are related to the image patches, thus exploiting more training signals at each training step. We investigated our methods on several image benchmarks finding that RelViT improves the SSL state-of-the-art methods by a large margin, especially on small datasets. Code is available at: https://github.com/guglielmocamporese/relvit.
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique c…
Measuring the similarity between patches in images is a fundamental building block in various tasks. Naturally, the patch-size has a major impact on the matching quality, and on the consequent application performance. We try to use large patches instead of relatively small patches so that each patch contains more information. We use different feature extraction mechanisms to extract the features of each individual image patches which forms a feature matrix and find out the nearest neighbor patches in the image. The nearest patches are calculated using two different nearest neighbor algorithms …
Institute of Neuroinformatics, University of Z\"urich；ETH Z\"urich, Z\"urich, Switzerland
Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to leverage its ability to process a variable-length input. The input to the ViT consists of events that are accumulated into time bins and spatially separated into non-overlapping sub-regions called patches. Patches are selected when the number of nonzero pixel locations within a sub-region is above a threshold. We show that by fine-tuning a ViT model on the se…
We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further de…
Universitat Autonoma de Barcelona（巴塞罗那自治大学）；Nanjing University of Science and Technology（南京理工大学）；Huawei Kirin Solution（华为麒麟解决方案）
Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might no longer align with the source domain classifier, still forms clear clusters. We capture this intrinsic structu…
The Weizmann Institute of Science（魏茨曼科学研究所）；Weizmann Artificial Intelligence Center (WAIC)（魏茨曼人工智能中心）
Single image generative models perform synthesis and manipulation tasks by capturing the distribution of patches within a single image. The classical (pre Deep Learning) prevailing approaches for these tasks are based on an optimization process that maximizes patch similarity between the input and generated output. Recently, however, Single Image GANs were introduced both as a superior solution for such manipulation tasks, but also for remarkable novel generative tasks. Despite their impressiveness, single image GANs require long training time (usually hours) for each image and each task. They…
University of Arkansas（阿肯色大学）；University of Minnesota（明尼苏达大学）；Massachusetts Institute of Technology（麻省理工学院）；Michigan Technological University（密歇根理工大学）；Texas A&M University（德克萨斯A&M大学）
The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted. This study marks the first attempt to cross-compare performances of popular state-of-the-art deep learning models in estimating population distribution from remote sensing images, investigate the contribution of neighboring effect, and explore the potential systematic population estimation biases. We conduct an end-to-end trainin…
Some images that are difficult to recognize on their own may become more clear in the context of a neighborhood of related images with similar social-network metadata. We build on this intuition to improve multilabel image annotation. Our model uses image metadata nonparametrically to generate neighborhoods of related images using Jaccard similarities, then uses a deep neural network to blend visual information from the image and its neighbors. Prior work typically models image metadata parametrically, in contrast, our nonparametric treatment allows our model to perform well even when the voca…
Indian Institute of Technology Indore（印度理工学院印多尔分校）
Breast cancer is becoming pervasive with each passing day. Hence, its early detection is a big step in saving the life of any patient. Mammography is a common tool in breast cancer diagnosis. The most important step here is classification of mammogram patches as normal-abnormal and benign-malignant. Texture of a breast in a mammogram patch plays a significant role in these classifications. We propose a variation of Histogram of Gradients (HOG) and Gabor filter combination called Histogram of Oriented Texture (HOT) that exploits this fact. We also revisit the Pass Band - Discrete Cosine Transfo…
Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Harbin Institute of Technology（哈尔滨工业大学）
Non-local self-similarity in natural images has been well studied as an effective prior in image restoration. However, for single image super-resolution (SISR), most existing deep non-local methods (e.g., non-local neural networks) only exploit similar patches within the same scale of the low-resolution (LR) input image. Consequently, the restoration is limited to using the same-scale information while neglecting potential high-resolution (HR) cues from other scales. In this paper, we explore the cross-scale patch recurrence property of a natural image, i.e., similar patches tend to recur many…
Sparsity constrained single image super-resolution (SR) has been of much recent interest. A typical approach involves sparsely representing patches in a low-resolution (LR) input image via a dictionary of example LR patches, and then using the coefficients of this representation to generate the high-resolution (HR) output via an analogous HR dictionary. However, most existing sparse representation methods for super resolution focus on the luminance channel information and do not capture interactions between color channels. In this work, we extend sparsity based super-resolution to multiple col…
Audi AG（奥迪股份公司）；Technische Hochschule Ingolstadt（因戈尔施塔特应用技术大学）
This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video. The second stage leverages a privacy-preserving Video Generative Adversarial Network designed to inpaint the missing image patches with artificially generated faces. Our initial experiments reveal that image based generative models are not capable of inpainting patches showing temporal coherent appearance across neighboring video frames. To address this …
Despite the popularity and empirical success of patch-based nearest-neighbor and weighted majority voting approaches to medical image segmentation, there has been no theoretical development on when, why, and how well these nonparametric methods work. We bridge this gap by providing a theoretical performance guarantee for nearest-neighbor and weighted majority voting segmentation under a new probabilistic model for patch-based image segmentation. Our analysis relies on a new local property for how similar nearby patches are, and fuses existing lines of work on modeling natural imagery patches a…
Frankfurt Institute for Advanced Studies（法兰克福高等研究院）；Xidian FIAS Joint Research Center（西电-法兰克福高等研究院联合研究中心）
The vision transformer (ViT) has achieved state-of-the-art results in various vision tasks. It utilizes a learnable position embedding (PE) mechanism to encode the location of each image patch. However, it is presently unclear if this learnable PE is really necessary and what its benefits are. This paper explores two alternative ways of encoding the location of individual patches that exploit prior knowledge about their spatial arrangement. One is called the sequence relationship embedding (SRE), and the other is called the circle relationship embedding (CRE). Among them, the SRE considers all…
INSA Rennes（雷恩国立应用科学学院）；Inria（法国国家信息与自动化研究所）；Technicolor（特艺集团）；University of Nantes（南特大学）；Telecom SudParis（南巴黎电信学院）；University of Glasgow（格拉斯哥大学）
Many multimedia information retrieval or machine learning problems require efficient high-dimensional nearest neighbor search techniques. For instance, multimedia objects (images, music or videos) can be represented by high-dimensional feature vectors. Finding two similar multimedia objects then comes down to finding two objects that have similar feature vectors. In the current context of mass use of social networks, large scale multimedia databases or large scale machine learning applications are more and more common, calling for efficient nearest neighbor search approaches. This thesis build…
Nanyang Technological University（南洋理工大学）；Michigan State University（密歇根州立大学）
Constructing effective image priors is critical to solving ill-posed inverse problems in image processing and imaging. Recent works proposed to exploit image non-local similarity for inverse problems by grouping similar patches and demonstrated state-of-the-art results in many applications. However, compared to classic methods based on filtering or sparsity, most of the non-local algorithms are time-consuming, mainly due to the highly inefficient and redundant block matching step, where the distance between each pair of overlapping patches needs to be computed. In this work, we propose a novel…
Inner Mongolia University（内蒙古大学）；University of Hong Kong（香港大学）
Non-local self-similarity based low rank algorithms are the state-of-the-art methods for image denoising. In this paper, a new method is proposed by solving two issues: how to improve similar patches matching accuracy and build an appropriate low rank matrix approximation model for Gaussian noise. For the first issue, similar patches can be found locally or globally. Local patch matching is to find similar patches in a large neighborhood which can alleviate noise effect, but the number of patches may be insufficient. Global patch matching is to determine enough similar patches but the error ra…
In this paper we present a Bayesian image zooming/super-resolution algorithm based on a patch based representation. We work on a patch based model with overlap and employ a Locally Linear Embedding (LLE) based approach as our data fidelity term in the Bayesian inference. The image prior imposes continuity constraints across the overlapping patches. We apply an error back-projection technique, with an approximate cross bilateral filter. The problem of nearest neighbor search is handled by a variant of the locality sensitive hashing (LSH) scheme. The novelty of our work lies in the speed up achi…
To guarantee a satisfying Quality of Experience (QoE) for consumers, it is required to measure image quality efficiently and reliably. The neglect of the high-level semantic information may result in predicting a clear blue sky as bad quality, which is inconsistent with human perception. Therefore, in this paper, we tackle this problem by exploiting the high-level semantics and propose a novel no-reference image quality assessment method for realistic blur images. Firstly, the whole image is divided into multiple overlapping patches. Secondly, each patch is represented by the high-level featur…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of California, Irvine（加利福尼亚大学尔湾分校）；ETH Zurich（苏黎世联邦理工学院）；Tongji University（同济大学）；Chinese University of Hong Kong（香港中文大学）
Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition. To this end, we make three main contributions from the following aspects. First, we propose a patch-level and end-to-end architecture to model the appearance of local patches, called {\em…
GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition
Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）
Manifold models consider natural-image patches to be on a low-dimensional manifold embedded in a high dimensional state space and each patch and its similar patches to approximately lie on a linear affine subspace. Manifold models are closely related to semi-local similarity, a well-known property of natural images, referring to that for most natural-image patches, several similar patches can be found in its spatial neighborhood. Many approaches to single image interpolation use manifold models to exploit semi-local similarity by two mutually exclusive parts: i) searching each target patch's s…
The paradigm of image-to-image translation is leveraged for the benefit of sketch stylization via transfer of geometric textural details. Lacking the necessary volumes of data for standard training of translation systems, we advocate for operation at the patch level, where a handful of stylized sketches provide ample mining potential for patches featuring basic geometric primitives. Operating at the patch level necessitates special consideration of full sketch translation, as individual translation of patches with no regard to neighbors is likely to produce visible seams and artifacts at patch…
This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges: (i) neighbor relations that determine the aggregation strength from intra-frame neighbors in space, and (ii) similarity relations that indicate the transition probability of inter-frame paths across time. Leveraging the cycle-consistency in videos, our contrastive learning objective discriminates dynamic objects from bot…
In this paper, we propose a novel image denoising algorithm exploiting features from both spatial as well as transformed domain. We implement intensity-invariance based improved grouping for collaborative support-agnostic sparse reconstruction. For collaboration firstly, we stack similar-structured patches via intensity-invariant correlation measure. The grouped patches collaborate to yield desirable sparse estimates for noise filtering. This is because similar patches share the same support in the transformed domain, such similar supports can be used as probabilities of active taps to refine …
Existing video super-resolution methods often utilize a few neighboring frames to generate a higher-resolution image for each frame. However, the redundant information between distant frames has not been fully exploited in these methods: corresponding patches of the same instance appear across distant frames at different scales. Based on this observation, we propose a video super-resolution method with long-term cross-scale aggregation that leverages similar patches (self-exemplars) across distant frames. Our model also consists of a multi-reference alignment module to fuse the features derive…
Non-local methods exploiting the self-similarity of natural signals have been well studied, for example in image analysis and restoration. Existing approaches, however, rely on k-nearest neighbors (KNN) matching in a fixed feature space. The main hurdle in optimizing this feature space w.r.t. application performance is the non-differentiability of the KNN selection rule. To overcome this, we propose a continuous deterministic relaxation of KNN selection that maintains differentiability w.r.t. pairwise distances, but retains the original KNN as the limit of a temperature parameter approaching z…
High-resolution image segmentation remains challenging and error-prone due to the enormous size of intermediate feature maps. Conventional methods avoid this problem by using patch based approaches where each patch is segmented independently. However, independent patch segmentation induces errors, particularly at the patch boundary due to the lack of contextual information in very high-resolution images where the patch size is much smaller compared to the full image. To overcome these limitations, in this paper, we propose a novel framework to segment a particular patch by incorporating contex…
University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
Techniques exploiting the sparsity of images in a transform domain have been effective for various applications in image and video processing. Transform learning methods involve cheap computations and have been demonstrated to perform well in applications such as image denoising and medical image reconstruction. Recently, we proposed methods for online learning of sparsifying transforms from streaming signals, which enjoy good convergence guarantees, and involve lower computational costs than online synthesis dictionary learning. In this work, we apply online transform learning to video denois…
Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel approach of exploiting scale-invariance property of the semantic segmentation model for self-supervised domain adaptation. Our algorithm is based on a reasonable assumption that, in general, regardless of the size of the object and stuff (given context) the semantic labeling should be unchanged. We show that this constraint is violated over the images of the target…
University of California, Davis（加州大学戴维斯分校）；Visa Research（Visa研究院）
Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the sequence to learn the attention between patches. Despite many successful interpretations of transformers on sequential data, little effort has been devoted to the interpretation of ViTs, and many questions remain unanswered. For example, among the numerous attention heads, which one is more important? How strong are individual patches attending to their spa…
Purdue University（普渡大学）；Politecnico di Milano（米兰理工大学）
Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information. Solving this problem has great impact on image integrity assessment as well as on authenticity verification. Recent advancements that use convolutional neural networks (CNNs) in the media forensic field have enabled camera model attribution methods to work well even on small image patches. These improvements are also important for …
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心（DLR））
The availability of curated large-scale training data is a crucial factor for the development of well-generalizing deep learning methods for the extraction of geoinformation from multi-sensor remote sensing imagery. While quite some datasets have already been published by the community, most of them suffer from rather strong limitations, e.g. regarding spatial coverage, diversity or simply number of available samples. Exploiting the freely available data acquired by the Sentinel satellites of the Copernicus program implemented by the European Space Agency, as well as the cloud computing facili…
The University of Tokyo（东京大学）；RIKEN（理化学研究所）；The Japanese Society of Pathology（日本病理学会）；Kyoto University（京都大学）；Tokyo Medical and Dental University（东京医科齿科大学）；National Institute of Informatics（国立信息学研究所）
Histopathological image analysis is an essential process for the discovery of diseases such as cancer. However, it is challenging to train CNN on whole slide images (WSIs) of gigapixel resolution considering the available memory capacity. Most of the previous works divide high resolution WSIs into small image patches and separately input them into the model to classify it as a tumor or a normal tissue. However, patch-based classification uses only patch-scale local information but ignores the relationship between neighboring patches. If we consider the relationship of neighboring patches and g…
Quantitative Susceptibility Mapping is a parametric imaging technique to estimate the magnetic susceptibilities of biological tissues from MRI phase measurements. This problem of estimating the susceptibility map is ill posed. Regularized recovery approaches exploiting signal properties such as smoothness and sparsity improve reconstructions, but suffer from over-smoothing artifacts. Deep learning approaches have shown great potential and generate maps with reduced artifacts. However, for reasonable reconstructions and network generalization, they require numerous training datasets resulting i…
Anhui University（安徽大学）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Sun Yat-Sen University（中山大学）；Harbin Institute of Technology（哈尔滨工业大学）；University of California, Merced（加州大学默塞德分校）
Existing visual tracking methods usually localize a target object with a bounding box, in which the performance of the foreground object trackers or detectors is often affected by the inclusion of background clutter. To handle this problem, we learn a patch-based graph representation for visual tracking. The tracked object is modeled by with a graph by taking a set of non-overlapping image patches as nodes, in which the weight of each node indicates how likely it belongs to the foreground and edges are weighted for indicating the appearance compatibility of two neighboring nodes. This graph is…
Fine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillation
Institute for Biomedical Informatics, Faculty of Medicine（医学院生物医学信息学研究所）；University Hospital Cologne, University of Cologne（科隆大学医院（科隆大学））；Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine（科隆分子医学中心（CMMC，医学院））
National Engineering Laboratory for Video Technology, Peking University（北京大学视频技术国家工程实验室）
In this letter, we propose a novel image denoising method based on correlation preserving sparse coding. Because the instable and unreliable correlations among basis set can limit the performance of the dictionary-driven denoising methods, two effective regularized strategies are employed in the coding process. Specifically, a graph-based regularizer is built for preserving the global similarity correlations, which can adaptively capture both the geometrical structures and discriminative features of textured patches. In particular, edge weights in the graph are obtained by seeking a nonnegativ…
