We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on solely learning global representations for an entire image, ReSim learns both regional representations for localization as well as semantic image-level representations. ReSim operates by sliding a fixed-sized window across the overlapping area between two views (e.g., image crops), aligning these areas with their corresponding convolutional feature map regions, and then maximizing the feature similarity across views. As a result, ReSim learns spatially and semantically consistent feature representation throughout the convolutional feature maps of a neural network. A shift or scale of an image region, e.g., a shift or scale of an object, has a corresponding change in the feature maps; this allows downstream tasks to leverage these representations for localization. Through object detection, instance segmentation, and dense pose estimation experiments, we illustrate how ReSim learns representations which significantly improve the localization and classification performance compared to a competitive MoCo-v2 baseline: $+2.7$ AP$^{\text{bb}}_{75}$ VOC, $+1.1$ AP$^{\text{bb}}_{75}$ COCO, and $+1.9$ AP$^{\text{mk}}$ Cityscapes. Code and pre-trained models are released at: \url{https://github.com/Tete-Xiao/ReSim}
Validation of image segmentation methods is of critical importance. Probabilistic image segmentation is increasingly popular as it captures uncertainty in the results. Image segmentation methods that support multi-region (as opposed to binary) delineation are more favourable as they capture interactions between the different objects in the image. The Dice similarity coefficient (DSC) has been a popular metric for evaluating the accuracy of automated or semi-automated segmentation methods by comparing their results to the ground truth. In this work, we develop an extension of the DSC to multi-r…
Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task. Existing methods simply leverage quantization loss and similarity loss, which result in unexpectedly biased back-propagating gradients and affect the search performances. To this end, we propose a novel gradient snapping layer …
Tsinghua University（清华大学）；State Key Lab of Intelligent Technologies and Systems（智能技术与系统国家重点实验室）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature space with high similarity, which usually leads to wrong pairwise relationship for large neighborhoods because the Euclidean distance fails to depict the true semantic similarity on the feature manifold. On the contrary, our method mines the feature manifold in an unsupervised manner, through which the semantic similarity among instances is learned in order to obtain discriminative representations. Specifically, we emplo…
This paper proposes integrating semantics-oriented similarity representation into RankingMatch, a recently proposed semi-supervised learning method. Our method, dubbed ReRankMatch, aims to deal with the case in which labeled and unlabeled data share non-overlapping categories. ReRankMatch encourages the model to produce the similar image representations for the samples likely belonging to the same class. We evaluate our method on various datasets such as CIFAR-10, CIFAR-100, SVHN, STL-10, and Tiny ImageNet. We obtain promising results (4.21% error rate on CIFAR-10 with 4000 labels, 22.32% erro…
Pre-trained Models Succeed in Medical Imaging with Representation Similarity Degradation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Chemical Sciences, University of Chinese Academy of Sciences（中国科学院大学化学科学学院）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
Yale University（耶鲁大学）；Microsoft AI for Good Research Lab（微软人工智能公益研究实验室）；Microsoft Research（微软研究院）
We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks. We derive a new training algorithm for epitomes which allows, for the first time, learning from very large data sets and derive a label super-resolution algorithm as a statistical inference algorithm over epitomic representations. We illustrate our methods on land cover mapping and medical image analysis tasks.
Microsoft India（微软印度公司）；Indian Institute of Technology Kharagpur（印度理工学院克勒格布尔分校）
Tabular structures are used to present crucial information in a structured and crisp manner. Detection of such regions is of great importance for proper understanding of a document. Tabular structures can be of various layouts and types. Therefore, detection of these regions is a hard problem. Most of the existing techniques detect tables from a document image by using prior knowledge of the structures of the tables. However, these methods are not applicable for generalized tabular structures. In this work, we propose a similarity measure to find similarities between pairs of rows in a tabular…
the Third Affiliated Hospital of Sun Yat-Sen University（中山大学附属第三医院）；School of Mathematical Sciences, Zhejiang University（浙江大学数学科学学院）；Henan Provincial People’s Hospital（河南省人民医院）
In this paper, a multi-scale framework with local region based active contour and boundary shape similarity constraint is proposed for the segmentation of levator hiatus in ultrasound images. In this paper, we proposed a multiscale active contour framework to segment levator hiatus ultrasound images by combining the local region information and boundary shape similarity constraint. In order to get more precisely initializations and reduce the computational cost, Gaussian pyramid method is used to decompose the image into coarse-to-fine scales. A localized region active contour model is firstly…
Convolution is conventionally defined as a linear operation on functions of one or more variables which commutes with shifts. Group convolution generalizes the concept to linear operations on functions of group elements representing more general geometric transformations and which commute with those transformations. Since similarity transformation is the most general geometric transformation on images that preserves shape, the group convolution that is equivariant to similarity transformation is the most general shape preserving linear operator. Because similarity transformations have four fre…
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；Ant Group（蚂蚁集团）
Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective, i.e., by formulating the representation learning scheme in a generative manner. Typically, the neighboring image patches among one text line tend to have similar styles, including the strokes, textures, colors, etc. Motivated by this common sense, we augment one image patch and use its neighboring patch as guidance to recover itself. Specifically, we propose a…
Humboldt-Universität zu Berlin（柏林洪堡大学）；University of Milano-Bicocca（米兰比可卡大学）
Over the last years, advancements in deep learning models for computer vision have led to a dramatic improvement in their image classification accuracy. However, models with a higher accuracy in the task they were trained on do not necessarily develop better image representations that allow them to also perform better in other tasks they were not trained on. In order to investigate the representation learning capabilities of prominent high-performing computer vision models, we investigated how well they capture various indices of perceptual similarity from large-scale behavioral datasets. We f…
Beijing University of Technology（北京工业大学）；Tsinghua University（清华大学）
Blind image deconvolution is the problem of recovering the latent image from the only observed blurry image when the blur kernel is unknown. In this paper, we propose an edge-based blur kernel estimation method for blind motion deconvolution. In our previous work, we incorporate both sparse representation and self-similarity of image patches as priors into our blind deconvolution model to regularize the recovery of the latent image. Since almost any natural image has properties of sparsity and multi-scale self-similarity, we construct a sparsity regularizer and a cross-scale non-local regulari…
We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn `distributional similarity' in a multimodal feature space by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the `image' side of image captioning, and vary the input image representation but keep the RNN text generation component of a CNN-RNN model constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (…
Deformable image registration is able to achieve fast and accurate alignment between a pair of images and thus plays an important role in many medical image studies. The current deep learning (DL)-based image registration approaches directly learn the spatial transformation from one image to another by leveraging a convolutional neural network, requiring ground truth or similarity metric. Nevertheless, these methods only use a global similarity energy function to evaluate the similarity of a pair of images, which ignores the similarity of regions of interest (ROIs) within images. Moreover, DL-…
Queen Mary University of London（伦敦玛丽女王大学）；University of Leicester（莱斯特大学）
The detection of nuclei and cells in histology images is of great value in both clinical practice and pathological studies. However, multiple reasons such as morphological variations of nuclei or cells make it a challenging task where conventional object detection methods cannot obtain satisfactory performance in many cases. A detection task consists of two sub-tasks, classification and localization. Under the condition of dense object detection, classification is a key to boost the detection performance. Considering this, we propose similarity based region proposal networks (SRPN) for nuclei …
Delft University of Technology（代尔夫特理工大学）；Facebook AI Research（脸书人工智能研究院）
Traditional techniques for measuring similarities between time series are based on handcrafted similarity measures, whereas more recent learning-based approaches cannot exploit external supervision. We combine ideas from time-series modeling and metric learning, and study siamese recurrent networks (SRNs) that minimize a classification loss to learn a good similarity measure between time series. Specifically, our approach learns a vectorial representation for each time series in such a way that similar time series are modeled by similar representations, and dissimilar time series by dissimilar…
Similarity-based representation factorization for revealing interpretable dimensions in representational data
Max Planck Institute for Human Cognitive and Brain Sciences（人类认知与脑科学最大平面研究所）；National Institute of Mental Health（心理健康国家研究所）；Justus Liebig University Giessen（吉森约斯特-利普大学）；Center for Mind, Brain and Behavior（心智、脑与行为中心）
MSDS: Deep Structural Similarity with Multiscale Representation
Fujian Key Lab for Intelligent Processing and Wireless Communication of Media Information, College of Physics and Information Engineering, Fuzhou University（福建省智能信息处理与无线通信重点实验室，物理与信息工程学院，福州大学）；School of Computing and Information Science, Fuzhou Institute of Technology（计算机与信息科学学院，福州理工学院）
LG AI Research（LG人工智能研究院）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embe…
Clustering is a difficult and widely-studied data mining task, with many varieties of clustering algorithms proposed in the literature. Nearly all algorithms use a similarity measure such as a distance metric (e.g. Euclidean distance) to decide which instances to assign to the same cluster. These similarity measures are generally pre-defined and cannot be easily tailored to the properties of a particular dataset, which leads to limitations in the quality and the interpretability of the clusters produced. In this paper, we propose a new approach to automatically evolving similarity functions fo…
Variational Adapter for Cross-modal Similarity Representation
School of Remote Sensing and Information Engineering（遥感与信息工程学院）；Wuhan University（武汉大学）；School of Data Science and Engineering（数据科学与工程学院）；East China Normal University（华东师范大学）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing（测绘遥感信息工程国家重点实验室）
Autodesk AI Lab（欧特克人工智能实验室）；Stanford University（斯坦福大学）；Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive information is particularly difficult for real-world datasets. In this work, we propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream performance. Our method leverages a perceptual similarity metric via a triplet loss to ensu…
George Washington University（乔治·华盛顿大学）；Temple University（天普大学）
For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for classification networks, but applicable to the problem domains better suited to similarity learning. The visualization shows how similarity networks that are fine-tuned learn to focus on different features. We also generalize our approach to embedding networks that use different pooling strategies and provide a simple mechanism to support image similarity se…
School of IoT Engineering, Jiangnan University（江南大学物联网工程学院）
A novel multi-focus image fusion algorithm performed in spatial domain based on similarity characteristics is proposed incorporating with region segmentation. In this paper, a new similarity measure is developed based on the structural similarity (SSIM) index, which is more suitable for multi-focus image segmentation. Firstly, the SSNSIM map is calculated between two input images. Then we segment the SSNSIM map using watershed method, and merge the small homogeneous regions with fuzzy c-means clustering algorithm (FCM). For three source images, a joint region segmentation method based on segme…
Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment
Graduate School of Arts and Science, University of Tokyo（东京大学艺术与科学研究生院）
Deep neural networks are increasingly being used in cognitive modeling as a means of deriving representations for complex stimuli such as images. While the predictive power of these networks is high, it is often not clear whether they also offer useful explanations of the task at hand. Convolutional neural network representations have been shown to be predictive of human similarity judgments for images after appropriate adaptation. However, these high-dimensional representations are difficult to interpret. Here we present a method for reducing these representations to a low-dimensional space w…
Stanford University（斯坦福大学）；University of Toronto（多伦多大学）；University of Tokyo（东京大学）
Many patterns in nature exhibit self-similarity: they can be compactly described via self-referential transformations. Said patterns commonly appear in natural and artificial objects, such as molecules, shorelines, galaxies and even images. In this work, we investigate the role of learning in the automated discovery of self-similarity and in its utilization for downstream tasks. To this end, we design a novel class of implicit operators, Neural Collages, which (1) represent data as the parameters of a self-referential, structured transformation, and (2) employ hypernetworks to amortize the cos…
Southeast University（东南大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Rennes 1（雷恩第一大学）；Western University（韦仕敦大学）；Case Western Reserve University（凯斯西储大学）
Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training, due to their sharing of numerous same semantic regions. However, the lack of the semantic prior in metrics and the semantic-independent variation in 3D medical images make it challenging to get a reliable measurement for the inter-image similarity, hindering the learning of consistent representation for same semantics. We investigate the challenging problem of this task, i.e., learning a consistent representation between images for a clustering effect of same semantic features. We propose a novel vis…
Geometric Similarity in VLM Low-Level Vision Representations
Duke University（杜克大学）；Texas A&M University（德克萨斯A&M大学）；Florida State University（佛罗里达州立大学）；UC San Diego（加州大学圣迭戈分校）；University of Pennsylvania（宾夕法尼亚大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar, sharing the decoder serves as an additional inductive bias providing more room for tasks to share complementary information among themselves. However, increased sharing exposes more parameters to task interference which likely hinders both generalization and robustness. Effective ways to curb this interference while exploiting the inductive bias of sharing …
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Evidation Health, Inc.（埃维达申健康公司）
We present a method to discover differences between populations with respect to the spatial coherence of their oriented white matter microstructure in arbitrarily shaped white matter regions. This method is applied to diffusion MRI scans of a subset of the Human Connectome Project dataset: 57 pairs of monozygotic and 52 pairs of dizygotic twins. After controlling for morphological similarity between twins, we identify 3.7% of all white matter as being associated with genetic similarity (35.1k voxels, $p < 10^{-4}$, false discovery rate 1.5%), 75% of which spatially clusters into twenty-two con…
Rochester Institute of Technology（罗切斯特理工学院）；Massachusetts Institute of Technology（麻省理工学院）；Philips Research North America（飞利浦北美研究院）
Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate. Most of the existing approaches are based on the application of various classification methods on explicitly extracted statistical features from vital signals. In this work, we propose to eliminate the high cost of engineering hand-crafted features from multivariate time-series of physiologic signals by learning their representation with a sequence-to-sequence auto-encoder. We then propose to hash the learned representations to enable signal similarity assessment for …
Neural networks trained on standard image classification data sets are shown to be less resistant to data set bias. It is necessary to comprehend the behavior objective function that might correspond to superior performance for data with biases. However, there is little research on the selection of the objective function and its representational structure when trained on data set with biases. In this paper, we investigate the performance and internal representational structure of convolution-based neural networks (e.g., ResNets) trained on biased data using various objective functions. We spec…
