Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on metric learning losses for augmentation and generalization. However, these methods require additional generative networks along with the main network, which can lead to a larger model size, slower training speed, and harder optimization. Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information. In this paper, inspired by query expansion and database augmentation, we propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair mining to learn with the most informative feature representations. Because of its simplicity and flexibility, it can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty. Finally, the combination of embedding expansion and representative metric learning losses outperforms the state-of-the-art losses and previous sample generation methods in both image retrieval and clustering tasks. The implementation is publicly available.
Samsung AI Center Moscow（三星莫斯科人工智能中心）；Swiss Federal Institute of Technology Lausanne (EPFL)（洛桑瑞士联邦理工学院（EPFL））；National Research University Higher School of Economics（国立研究型大学高等经济学院）
Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as search, matching, and recommendation systems, heavily rely on embeddings. Unfortunately, due to misalignment of features of independently trained models, embeddings, cannot be improved with a naive deep ensemble like approach. In this work, we look at the ensembling of representations and propose mean embeddings with test-time augmentation (MeTTA) simple yet well-performing reci…
Self-supervised learning aims to learn a embedding space where semantically similar samples are close. Contrastive learning methods pull views of samples together and push different samples away, which utilizes semantic invariance of augmentation but ignores the relationship between samples. To better exploit the power of augmentation, we observe that semantically similar samples are more likely to have similar augmented views. Therefore, we can take the augmented views as a special description of a sample. In this paper, we model such a description as the augmentation distribution and we call…
Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering
College of Information Science and Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）；Beijing University of Technology（北京工业大学）；The University of Sydney Business School, The University of Sydney（悉尼大学商学院）
Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this paper, we develop a novel mechanism, the independent domain embedding augmentation learning ({IDEAL}) method. It can simultaneously learn multiple independent embedding spaces for multiple domains generated by predefined data transformations. Our IDEAL is orthogonal to existing DML techniques and can be seamlessly combined with prior DML approaches for enha…
Jilin University（吉林大学）；Megvii Inc.（旷视科技）；Beihang University（北京航空航天大学）；Huazhong University of Science and Technology（华中科技大学）；Tsinghua University（清华大学）
This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from th…
Contrastive learning has emerged as a premier method for learning representations with or without supervision. Recent studies have shown its utility in graph representation learning for pre-training. Despite successes, the understanding of how to design effective graph augmentations that can capture structural properties common to many different types of downstream graphs remains incomplete. We propose a set of well-motivated graph transformation operations derived via graph spectral analysis to provide a bank of candidates when constructing augmentations for a graph contrastive objective, ena…
We introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation sequentially: cutoff and PCA jittering. While pretraining steps proceed, we apply curriculum learning by incrementing the augmentation degree for each difficulty step. After data augmentation is finished, contrastive learning is applied on projected embeddings of original and augmented examples. When finetuned on GLUE benchmark, our model outperforms baseline models, especially fo…
The Chinese University of Hong Kong（香港中文大学）；Australian National University（澳大利亚国立大学）；Data61/CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）
Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA on various downstream tasks. The graph augmentation step is a vital but scarcely studied step of GCL. In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks. Thus, instead of investigating graph augmentation in the input space, we alternatively propose to perform augmentations on the hidden features (feature augmentation). Inspired by so-called matrix sketching, we …
Embeddings of high-dimensional data are widely used to explore data, to verify analysis results, and to communicate information. Their explanation, in particular with respect to the input attributes, is often difficult. With linear projects like PCA the axes can still be annotated meaningfully. With non-linear projections this is no longer possible and alternative strategies such as attribute-based color coding are required. In this paper, we review existing augmentation techniques and discuss their limitations. We present the Non-Linear Embeddings Surveyor (NoLiES) that combines a novel augme…
Eindhoven University of Technology（埃因霍温理工大学）；Cyclomedia B.V（Cyclomedia公司）
Vehicle re-identification plays a crucial role in the management of transportation infrastructure and traffic flow. However, this is a challenging task due to the large view-point variations in appearance, environmental and instance-related factors. Modern systems deploy CNNs to produce unique representations from the images of each vehicle instance. Most work focuses on leveraging new losses and network architectures to improve the descriptiveness of these representations. In contrast, our work concentrates on re-ranking and embedding expansion techniques. We propose an efficient approach for…
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation techniques are usually exploited to help enforce desired invariances within the learned representations, improving performance on various audio tasks thanks to more robust embeddings. Now, selecting the most relevant augmentations has proven crucial for better downstream performances. Thus, this work introduces a conditional independance-based method which all…
For the visible-infrared person re-identification (VIReID) task, one of the major challenges is the modality gaps between visible (VIS) and infrared (IR) images. However, the training samples are usually limited, while the modality gaps are too large, which leads that the existing methods cannot effectively mine diverse cross-modality clues. To handle this limitation, we propose a novel augmentation network in the embedding space, called diverse embedding expansion network (DEEN). The proposed DEEN can effectively generate diverse embeddings to learn the informative feature representations and…
Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstruction
School of Computer Engineering, Iran University of Science and Technology（伊朗科技大学计算机工程学院）；Technical and Engineering Faculty, South Tehran Branch, Islamic Azad University（伊斯兰阿扎德大学南德黑兰分校技术与工程学院）；Faculty of Engineering, University of Birjand（比尔詹德大学工程学院）；Faculty of Computer Engineering & Information Technology, Shahrood University of Technology（沙赫鲁德工业大学计算机工程与信息技术学院）
TU Darmstadt（达姆施塔特工业大学）；Huazhong University of Science and Technology（华中科技大学）
Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent dynamics or invariance to data augmentation have been shown to greatly improve the sample efficiency of the reinforcement learning algorithm and the generalizability of the learned embedding. We further argue, that explicitly improving Markovianity of the learned embedding is desirable and propose a self-supervised representation learning method which integrat…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Self-supervised representation learning of biological sequence embeddings alleviates computational resource constraints on downstream tasks while circumventing expensive experimental label acquisition. However, existing methods mostly borrow directly from large language models designed for NLP, rather than with bioinformatics philosophies in mind. Recently, contrastive mutual information maximization methods have achieved state-of-the-art representations for ImageNet. In this perspective piece, we discuss how viewing evolution as natural sequence augmentation and maximizing information across …
University of Southern California（南加利福尼亚大学）；Clarifai Inc（克拉里菲人工智能公司）；Northeastern University（东北大学）
Recent advances in the field of artificial intelligence have been made possible by deep neural networks. In applications where data are scarce, transfer learning and data augmentation techniques are commonly used to improve the generalization of deep learning models. However, fine-tuning a transfer model with data augmentation in the raw input space has a high computational cost to run the full network for every augmented input. This is particularly critical when large models are implemented on embedded devices with limited computational and energy resources. In this work, we propose a method …
Seoul National University（首尔国立大学）；Chung-Ang University（中央大学）；NAVER Clova
Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images to be mixed has not been elucidated in the literature: only the naive K-image expansion has been shown to lead to performance degradation. This study derives a new K-image mixing augmentation based on the stick-breaking process under Dirichlet prior distribution. We demonstrate the superiority of our K-image expansion augmentation over conventional two-image…
Dali University（大理大学）；Liuzhou Vocational & Technical College（柳州职业技术学院）；The Second Xiangya Hospital of Central South University（中南大学湘雅二医院）；Hunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer（湖南省肺癌早期诊断与精准治疗重点实验室）；Early-Stage Lung Cancer Center（早期肺癌中心）
Detection of pulmonary nodules by CT is used for screening lung cancer in early stages.omputer aided diagnosis (CAD) based on deep-learning method can identify the suspected areas of pulmonary nodules in CT images, thus improving the accuracy and efficiency of CT diagnosis. The accuracy and robustness of deep learning models. Method:In this paper, we explore (1) the data augmentation method based on the generation model and (2) the model structure improvement method based on the embedding mechanism. Two strategies have been introduced in this study: a new data augmentation method and a embeddi…
This article presents an efficient way to produce feature-rich, high-dimensionality embedding spaces from real-life images. The features produced are designed to be independent from augmentations used in real-life cases which appear on social media. Our approach uses convolutional neural networks (CNN) to produce an embedding space. An ArcFace head was used to train the model by employing automatically produced augmentations. Additionally, we present a way to make an ensemble out of different embeddings containing the same semantic information, a way to normalize the resulting embedding using …
University College London（伦敦大学学院）；Brigham and Women's Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Massachusetts General Hospital（麻省总医院）；Broad Institute of Harvard and MIT（哈佛-麻省理工博德研究所）；Dana-Farber Cancer Institute（达纳-法伯癌症研究所）；University of Warwick（华威大学）；University Hospitals Coventry and Warwickshire NHS Trust（考文垂与沃里克郡国民保健服务信托大学医院）；The Alan Turing Institute（艾伦·图灵研究所）
Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs' limited RAM. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than …
Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResNet Convolutional Neural Network as encoder to extract features from images, Hierarchical Context based Word Embeddings for word representations and a Deep Stacked Long Short Term Memory network as decoder, in addition to using Image Data Augmentation to avoid over-fitting. For data Augmentation, we use Horizontal and Vertical Flipping in addition to Perspective Transformations …
In recognition-based action interaction, robots' responses to human actions are often pre-designed according to recognized categories and thus stiff. In this paper, we specify a new Interactive Action Translation (IAT) task which aims to learn end-to-end action interaction from unlabeled interactive pairs, removing explicit action recognition. To enable learning on small-scale data, we propose a Paired-Embedding (PE) method for effective and reliable data augmentation. Specifically, our method first utilizes paired relationships to cluster individual actions in an embedding space. Then two act…
Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning
Computational Health Center & Helmholtz AI, Helmholtz Munich（计算健康中心与亥姆霍兹AI，亥姆霍兹慕尼黑）；Computer Aided Medical Procedures, Technical University of Munich（计算机辅助医疗程序，慕尼黑工业大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Department of Medicine III, Ludwig Maximilian University Hospital（路德维希·马克西米利安大学医院第三内科）；Department of Physics, Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学物理系）；DKTK, German Cancer Consortium, partner site Munich（德国癌症联盟DKTK，慕尼黑合作站点）
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model decision quality substantially. In this paper, we propose a novel image text retrieval technique, referred to as robust visual semantic embedding (RVSE), which consists of novel image-based and text-based augmentation techniques called semantic preserving augmentation for image (SPAugI) and text (SPAugT). Sinc…
Institute of Advanced Research in Artificial Intelligence (IARAI)（人工智能高级研究院（IARAI））；Athena RC（雅典娜研究中心）；Inria（法国国家信息与自动化研究所）；Univ Rennes（雷恩大学）；CNRS（法国国家科学研究中心）；IRISA（法国雷恩信息系统与随机系统研究所）
Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Yet, its extensions focus on the definition of interpolation and the space where it takes place, while the augmentation itself is less studied: For a mini-batch of size $m$, most methods interpolate between $m$ pairs with a single scalar interpolation factor $λ$. In this work, we make progress in this direction by introducing MultiMix, which interpolates an arbitrary number $n$ of tuples, each of length $m$, with one vector $λ$ per tuple. On sequence data, we fur…
Oftentimes, patterns can be represented through different modalities. For example, leaf data can be in the form of images or contours. Handwritten characters can also be either online or offline. To exploit this fact, we propose the use of self-augmentation and combine it with multi-modal feature embedding. In order to take advantage of the complementary information from the different modalities, the self-augmented multi-modal feature embedding employs a shared feature space. Through experimental results on classification with online handwriting and leaf images, we demonstrate that the propose…
Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis
IDP Institute（IDP研究所）；UMR CNRS 7013（法国国家科学研究中心UMR 7013）；University of Orleans（奥尔良大学）；PRISME Laboratory（PRISME实验室）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Geneva University Hospital（日内瓦大学医院）
