In the field of Earth Observation (EO), Continual Learning (CL) algorithms have been proposed to deal with large datasets by decomposing them into several subsets and processing them incrementally. The majority of these algorithms assume that data is (a) coming from a single source, and (b) fully labeled. Real-world EO datasets are instead characterized by a large heterogeneity (e.g., coming from aerial, satellite, or drone scenarios), and for the most part they are unlabeled, meaning they can be fully exploited only through the emerging Self-Supervised Learning (SSL) paradigm. For these reasons, in this paper we propose a new algorithm for merging SSL and CL for remote sensing applications, that we call Continual Barlow Twins (CBT). It combines the advantages of one of the simplest self-supervision techniques, i.e., Barlow Twins, with the Elastic Weight Consolidation method to avoid catastrophic forgetting. In addition, for the first time we evaluate SSL methods on a highly heterogeneous EO dataset, showing the effectiveness of these strategies on a novel combination of three almost non-overlapping domains datasets (airborne Potsdam dataset, satellite US3D dataset, and drone UAVid dataset), on a crucial downstream task in EO, i.e., semantic segmentation. Encouraging results show the superiority of SSL in this setting, and the effectiveness of creating an incremental effective pretrained feature extractor, based on ResNet50, without the need of relying on the complete availability of all the data, with a valuable saving of time and resources.
Facebook AI Research（脸书人工智能研究院）；New York University（纽约大学）
Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant solutions. Most current methods avoid such solutions by careful implementation details. We propose an objective function that naturally avoids collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and makin…
Indian Institute of Information Technology Allahabad（阿拉哈巴德印度信息技术学院）
Deep learning has brought the most profound contribution towards biomedical image segmentation to automate the process of delineation in medical imaging. To accomplish such task, the models are required to be trained using huge amount of annotated or labelled data that highlights the region of interest with a binary mask. However, efficient generation of the annotations for such huge data requires expert biomedical analysts and extensive manual effort. It is a tedious and expensive task, while also being vulnerable to human error. To address this problem, a self-supervised learning framework, …
Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers
HSLU, Lucerne University of Applied Sciences and Arts（卢塞恩应用科学与艺术大学）；Technical University of Munich（慕尼黑技术大学）；University College London (UCL)（伦敦大学学院）；TOELT LLC AI lab（TOELT LLC人工智能实验室）
The generalisation performance of a convolutional neural networks (CNN) is majorly predisposed by the quantity, quality, and diversity of the training images. All the training data needs to be annotated in-hand before, in many real-world applications data is easy to acquire but expensive and time-consuming to label. The goal of the Active learning for the task is to draw most informative samples from the unlabeled pool which can used for training after annotation. With total different objective, self-supervised learning which have been gaining meteoric popularity by closing the gap in performa…
Identifying the camera pose for a given image is a challenging problem with applications in robotics, autonomous vehicles, and augmented/virtual reality. Lately, learning-based methods have shown to be effective for absolute camera pose estimation. However, these methods are not accurate when generalizing to different domains. In this paper, a domain adaptive training framework for absolute pose regression is introduced. In the proposed framework, the scene image is augmented for different domains by using generative methods to train parallel branches using Barlow Twins objective. The parallel…
Efficient Self-Supervised Barlow Twins from Limited Tissue Slide Cohorts for Colonic Pathology Diagnostics
University of Concordia（康考迪亚大学）；University of Montreal（蒙特利尔大学）；Sunnybrook Health Science Centre（桑尼布鲁克健康科学中心）；Kingston General Hospital（金斯顿总医院）；Mila–Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）
Rochester Institute of Technology（罗切斯特理工学院）；Paige；Cornell Tech（康奈尔科技学院）
In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale image classification tasks, such as ImageNet. State-of-the-art continual learning methods use an initial supervised pre-training phase, in which the first 10% - 50% of the classes in a dataset are used to learn representations in an offline manner before continual learning of new classes begins. We hypothesize that self-supervised pre-training could yield features that generaliz…
North Shore Country Day（北岸乡村日校）；Northwestern University（西北大学）
Data labeling is often the most challenging task when developing computational pathology models. Pathologist participation is necessary to generate accurate labels, and the limitations on pathologist time and demand for large, labeled datasets has led to research in areas including weakly supervised learning using patient-level labels, machine assisted annotation and active learning. In this paper we explore self-supervised learning to reduce labeling burdens in computational pathology. We explore this in the context of classification of breast cancer tissue using the Barlow Twins approach, an…
Catastrophic forgetting in neural networks is a significant problem for continual learning. A majority of the current methods replay previous data during training, which violates the constraints of an ideal continual learning system. Additionally, current approaches that deal with forgetting ignore the problem of catastrophic remembering, i.e. the worsening ability to discriminate between data from different tasks. In our work, we introduce Relevance Mapping Networks (RMNs) which are inspired by the Optimal Overlap Hypothesis. The mappings reflects the relevance of the weights for the task at …
Advanced Research Lab, NavInfo Europe（NavInfo欧洲高级研究实验室）
Scene change detection (SCD), a crucial perception task, identifies changes by comparing scenes captured at different times. SCD is challenging due to noisy changes in illumination, seasonal variations, and perspective differences across a pair of views. Deep neural network based solutions require a large quantity of annotated data which is tedious and expensive to obtain. On the other hand, transfer learning from large datasets induces domain shift. To address these challenges, we propose a novel \textit{Differencing self-supervised pretraining (DSP)} method that uses feature differencing to …
RIKEN AIP（理化学研究所先进智能项目中心）；Carnegie Mellon University（卡内基梅隆大学）；Centre Henri Becquerel - Unicancer（亨利·贝克勒尔中心-法国癌症中心联盟）；Kyoto University（京都大学）
Recent developments in self-supervised learning give us the possibility to further reduce human intervention in multi-step pipelines where the focus evolves around particular objects of interest. In the present paper, the focus lays in the nuclei in histopathology images. In particular we aim at extracting cellular information in an unsupervised manner for a downstream task. As nuclei present themselves in a variety of sizes, we propose a new Scale-dependant convolutional layer to bypass scaling issues when resizing nuclei. On three nuclei datasets, we benchmark the following methods: handcraf…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Tsinghua University（清华大学）
German Aerospace Center (DLR)（德国航空航天中心）；Technical University of Munich (TUM)（慕尼黑工业大学）；Inria（法国国家信息与自动化研究所）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）
Deep learning has proven to be a very effective approach for Hyperspectral Image (HSI) classification. However, deep neural networks require large annotated datasets to generalize well. This limits the applicability of deep learning for HSI classification, where manually labelling thousands of pixels for every scene is impractical. In this paper, we propose to leverage Self Supervised Learning (SSL) for HSI classification. We show that by pre-training an encoder on unlabeled pixels using Barlow-Twins, a state-of-the-art SSL algorithm, we can obtain accurate models with a handful of labels. Exp…
Prospects for Mitigating Spectral Variability in Tropical Species Classification Using Self-Supervised Learning
AMAP；Univ Montpellier（蒙彼利埃大学）；CIRAD（法国农业发展研究国际合作中心）；CNRS（法国国家科学研究中心）；INRAE（法国国家农业、食品与环境研究院）；IRD（法国发展研究院）；Technical University of Munich（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；Grenoble INP（格勒诺布尔理工学院）；LJK（约瑟夫·傅里叶实验室）
Computer-aided diagnosis (CAD) can help pathologists improve diagnostic accuracy together with consistency and repeatability for cancers. However, the CAD models trained with the histopathological images only from a single center (hospital) generally suffer from the generalization problem due to the straining inconsistencies among different centers. In this work, we propose a pseudo-data based self-supervised federated learning (FL) framework, named SSL-FT-BT, to improve both the diagnostic accuracy and generalization of CAD models. Specifically, the pseudo histopathological images are generat…
Tsinghua University（清华大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；SenseTime Research（商汤科技研究院）；Zhejiang University（浙江大学）
Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised learning from different perspectives: (1) contrastive learning methods (e.g., MoCo, SimCLR) utilize both positive and negative samples to guide the training direction; (2) asymmetric network methods (e.g., BYOL, SimSiam) get rid of negative samples via the introduction of a predictor network and the stop-gradient operation; (3) feature decorrelation methods (e.g., Barlow Twins, VICReg) instead aim to reduce the redu…
Self-supervised representation learning maps high-dimensional data into a meaningful embedding space, where samples of similar semantic contents are close to each other. Most of the recent representation learning methods maximize cosine similarity or minimize the distance between the embedding features of different views from the same sample usually on the $l2$ normalized unit hypersphere. To prevent the trivial solutions that all samples have the same embedding feature, various techniques have been developed, such as contrastive learning, stop gradient, variance and covariance regularization,…
New York University（纽约大学）；Viasat, Inc.（Viasat公司）；Facebook AI Research（脸书人工智能研究院）
We present Transformation Invariance and Covariance Contrast (TiCo) for self-supervised visual representation learning. Similar to other recent self-supervised learning methods, our method is based on maximizing the agreement among embeddings of different distorted versions of the same image, which pushes the encoder to produce transformation invariant representations. To avoid the trivial solution where the encoder generates constant vectors, we regularize the covariance matrix of the embeddings from different images by penalizing low rank solutions. By jointly minimizing the transformation i…
Self-supervised learning unveils change in urban housing from street-level images
Swiss Data Science Center, ETH Zurich and EPFL（瑞士数据科学中心，苏黎世联邦理工学院与洛桑联邦理工学院）；NADEL - Center for Development and Cooperation, ETH Zurich（NADEL发展与合作中心，苏黎世联邦理工学院）；University College London（伦敦大学学院）；Centre for Advanced Spatial Analysis, University College London（伦敦大学学院高级空间分析中心）
Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those produced by SSL on downstream vision tasks. Inspired by this advancement and primarily motivated by the emergence of tabular and structured document image applications, we investigate which self-supervised pretraining objectives, architectures, and fine-tuning strategies are most effective. To address these questions, we introduce RegCLR, a new self-supervised framework that combi…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Heidelberg University（海德堡大学）
The technical advances in Computed Tomography (CT) allow to obtain immense amounts of 3D data. For such datasets it is very costly and time-consuming to obtain the accurate 3D segmentation markup to train neural networks. The annotation is typically done for a limited number of 2D slices, followed by an interpolation. In this work, we propose a pre-training method SortingLoss. It performs pre-training on slices instead of volumes, so that a model could be fine-tuned on a sparse set of slices, without the interpolation step. Unlike general methods (e.g. SimCLR or Barlow Twins), the task specifi…
Oregon State Univ.（俄勒冈州立大学）；Google Inc.（谷歌公司）；IBM Research（IBM研究院）
Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancing representation learning. Natural views are often handled by multiview analysis tools, e.g., (deep) canonical correlation analysis [(D)CCA], while the artificial ones are frequently used in self-supervised learning (SSL) paradigms, e.g., BYOL and Barlow Twins. Both types of approaches often involve learning neural feature extractors such that the embeddings of data exhibit high cross-view correlations. Although intu…
