PyTorchKR Papers

최신 논문

총 5,358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.01534공식 코드 · Papers with Code

Multi-modal Masked Autoencoders Learn Compositional Histopathological Representations

Self-supervised learning (SSL) enables learning useful inductive biases through utilizing pretext tasks that require no labels. The unlabeled nature of SSL makes it especially important for whole slide histopathological images (WSIs), where patch-level human annotation is difficult. Masked Autoencoders (MAE) is a recent SSL method suitable for digital pathology as it does not require negative sampling and requires little to no data augmentations. However, the domain shift between natural images and digital pathology images requires further research in designing MAE for patch-level WSIs. In this paper, we investigate several design choices for MAE in histopathology. Furthermore, we introduce a multi-modal MAE (MMAE) that leverages the specific compositionality of Hematoxylin & Eosin (H&E) stained WSIs. We performed our experiments on the public patch-level dataset NCT-CRC-HE-100K. The results show that the MMAE architecture outperforms supervised baselines and other state-of-the-art SSL techniques for an eight-class tissue phenotyping task, utilizing only 100 labeled samples for fine-tuning. Our code is available at https://github.com/wisdomikezogwo/MMAE_Pathology

arXiv:2209.02370공식 코드 · Papers with Code

Continual Learning, Fast and Slow

According to the Complementary Learning Systems (CLS) theory~\cite{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for rapid learning of the specifics, individual experiences; and a slow learning system located in the neocortex for the gradual acquisition of structured knowledge about the environment. Motivated by this theory, we propose \emph{DualNets} (for Dual Networks), a general continual learning framework comprising a fast learning system for supervised learning of pattern-separated representation from specific tasks and a slow learning system for representation learning of task-agnostic general representation via Self-Supervised Learning (SSL). DualNets can seamlessly incorporate both representation types into a holistic framework to facilitate better continual learning in deep neural networks. Via extensive experiments, we demonstrate the promising results of DualNets on a wide range of continual learning protocols, ranging from the standard offline, task-aware setting to the challenging online, task-free scenario. Notably, on the CTrL~\cite{veniat2020efficient} benchmark that has unrelated tasks with vastly different visual images, DualNets can achieve competitive performance with existing state-of-the-art dynamic architecture strategies~\cite{ostapenko2021continual}. Furthermore, we conduct comprehensive ablation studies to validate DualNets efficacy, robustness, and scalability. Code will be made available at \url{https://github.com/phquang/DualNet}.

arXiv:2209.02241

Real-Time Cattle Interaction Recognition via Triple-stream Network

In stockbreeding of beef cattle, computer vision-based approaches have been widely employed to monitor cattle conditions (e.g. the physical, physiology, and health). To this end, the accurate and effective recognition of cattle action is a prerequisite. Generally, most existing models are confined to individual behavior that uses video-based methods to extract spatial-temporal features for recognizing the individual actions of each cattle. However, there is sociality among cattle and their interaction usually reflects important conditions, e.g. estrus, and also video-based method neglects the real-time capability of the model. Based on this, we tackle the challenging task of real-time recognizing interactions between cattle in a single frame in this paper. The pipeline of our method includes two main modules: Cattle Localization Network and Interaction Recognition Network. At every moment, cattle localization network outputs high-quality interaction proposals from every detected cattle and feeds them into the interaction recognition network with a triple-stream architecture. Such a triple-stream network allows us to fuse different features relevant to recognizing interactions. Specifically, the three kinds of features are a visual feature that extracts the appearance representation of interaction proposals, a geometric feature that reflects the spatial relationship between cattle, and a semantic feature that captures our prior knowledge of the relationship between the individual action and interaction of cattle. In addition, to solve the problem of insufficient quantity of labeled data, we pre-train the model based on self-supervised learning. Qualitative and quantitative evaluation evidences the performance of our framework as an effective method to recognize cattle interaction in real time.

arXiv:2209.01712

ChemBERTa-2: Towards Chemical Foundation Models

Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that can be used to readily finetune on a wide variety of downstream tasks. We investigate the possibility of transferring such advances to molecular machine learning by building a chemical foundation model, ChemBERTa-2, using the language of SMILES. While labeled data for molecular prediction tasks is typically scarce, libraries of SMILES strings are readily available. In this work, we build upon ChemBERTa by optimizing the pretraining process. We compare multi-task and self-supervised pretraining by varying hyperparameters and pretraining dataset size, up to 77M compounds from PubChem. To our knowledge, the 77M set constitutes one of the largest datasets used for molecular pretraining to date. We find that with these pretraining improvements, we are competitive with existing state-of-the-art architectures on the MoleculeNet benchmark suite. We analyze the degree to which improvements in pretraining translate to improvement on downstream tasks.

arXiv:2209.01275

Feature diversity in self-supervised learning

Many studies on scaling laws consider basic factors such as model size, model shape, dataset size, and compute power. These factors are easily tunable and represent the fundamental elements of any machine learning setup. But researchers have also employed more complex factors to estimate the test error and generalization performance with high predictability. These factors are generally specific to the domain or application. For example, feature diversity was primarily used for promoting syn-to-real transfer by Chen et al. (2021). With numerous scaling factors defined in previous works, it would be interesting to investigate how these factors may affect overall generalization performance in the context of self-supervised learning with CNN models. How do individual factors promote generalization, which includes varying depth, width, or the number of training epochs with early stopping? For example, does higher feature diversity result in higher accuracy held in complex settings other than a syn-to-real transfer? How do these factors depend on each other? We found that the last layer is the most diversified throughout the training. However, while the model's test error decreases with increasing epochs, its diversity drops. We also discovered that diversity is directly related to model width.

arXiv:2209.00990

Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning

In this paper, we propose a self-supervised learning solution for human activity recognition with smartphone accelerometer data. We aim to develop a model that learns strong representations from accelerometer signals, in order to perform robust human activity classification, while reducing the model's reliance on class labels. Specifically, we intend to enable cross-dataset transfer learning such that our network pre-trained on a particular dataset can perform effective activity classification on other datasets (successive to a small amount of fine-tuning). To tackle this problem, we design our solution with the intention of learning as much information from the accelerometer signals as possible. As a result, we design two separate pipelines, one that learns the data in time-frequency domain, and the other in time-domain alone. In order to address the issues mentioned above in regards to cross-dataset transfer learning, we use self-supervised contrastive learning to train each of these streams. Next, each stream is fine-tuned for final classification, and eventually the two are fused to provide the final results. We evaluate the performance of the proposed solution on three datasets, namely MotionSense, HAPT, and HHAR, and demonstrate that our solution outperforms prior works in this field. We further evaluate the performance of the method in learning generalized features, by using MobiAct dataset for pre-training and the remaining three datasets for the downstream classification task, and show that the proposed solution achieves better performance in comparison with other self-supervised methods in cross-dataset transfer learning.

arXiv:2209.00945

IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applications

Pre-training representations acquired via self-supervised learning could achieve high accuracy on even tasks with small training data. Unlike in vision and natural language processing domains, pre-training for IMU-based applications is challenging, as there are few public datasets with sufficient size and diversity to learn generalizable representations. To overcome this problem, we propose IMG2IMU that adapts pre-trained representation from large-scale images to diverse IMU sensing tasks. We convert the sensor data into visually interpretable spectrograms for the model to utilize the knowledge gained from vision. We further present a sensor-aware pre-training method for images that enables models to acquire particularly impactful knowledge for IMU sensing applications. This involves using contrastive learning on our augmentation set customized for the properties of sensor data. Our evaluation with four different IMU sensing tasks shows that IMG2IMU outperforms the baselines pre-trained on sensor data by an average of 9.6%p F1-score, illustrating that vision knowledge can be usefully incorporated into IMU sensing applications where only limited training data is available.

arXiv:2209.00915

Detection of diabetic retinopathy using longitudinal self-supervised learning

Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression towards earlier and better patient-specific pathology management. However, conventional approaches for detecting diabetic retinopathy (DR) rarely take advantage of longitudinal information to improve DR analysis. In this work, we investigate the benefit of exploiting self-supervised learning with a longitudinal nature for DR diagnosis purposes. We compare different longitudinal self-supervised learning (LSSL) methods to model the disease progression from longitudinal retinal color fundus photographs (CFP) to detect early DR severity changes using a pair of consecutive exams. The experiments were conducted on a longitudinal DR screening dataset with or without those trained encoders (LSSL) acting as a longitudinal pretext task. Results achieve an AUC of 0.875 for the baseline (model trained from scratch) and an AUC of 0.96 (95% CI: 0.9593-0.9655 DeLong test) with a p-value < 2.2e-16 on early fusion using a simple ResNet alike architecture with frozen LSSL weights, suggesting that the LSSL latent space enables to encode the dynamic of DR progression.

arXiv:2209.00835

Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstruction

Recently, score-based diffusion models have shown satisfactory performance in MRI reconstruction. Most of these methods require a large amount of fully sampled MRI data as a training set, which, sometimes, is difficult to acquire in practice. This paper proposes a fully-sampled-data-free score-based diffusion model for MRI reconstruction, which learns the fully sampled MR image prior in a self-supervised manner on undersampled data. Specifically, we first infer the fully sampled MR image distribution from the undersampled data by Bayesian deep learning, then perturb the data distribution and approximate their probability density gradient by training a score function. Leveraging the learned score function as a prior, we can reconstruct the MR image by performing conditioned Langevin Markov chain Monte Carlo (MCMC) sampling. Experiments on the public dataset show that the proposed method outperforms existing self-supervised MRI reconstruction methods and achieves comparable performances with the conventional (fully sampled data trained) score-based diffusion methods.

arXiv:2209.00782

BinImg2Vec: Augmenting Malware Binary Image Classification with Data2Vec

Rapid digitalisation spurred by the Covid-19 pandemic has resulted in more cyber crime. Malware-as-a-service is now a booming business for cyber criminals. With the surge in malware activities, it is vital for cyber defenders to understand more about the malware samples they have at hand as such information can greatly influence their next course of actions during a breach. Recently, researchers have shown how malware family classification can be done by first converting malware binaries into grayscale images and then passing them through neural networks for classification. However, most work focus on studying the impact of different neural network architectures on classification performance. In the last year, researchers have shown that augmenting supervised learning with self-supervised learning can improve performance. Even more recently, Data2Vec was proposed as a modality agnostic self-supervised framework to train neural networks. In this paper, we present BinImg2Vec, a framework of training malware binary image classifiers that incorporates both self-supervised learning and supervised learning to produce a model that consistently outperforms one trained only via supervised learning. We were able to achieve a 4% improvement in classification performance and a 0.5% reduction in performance variance over multiple runs. We also show how our framework produces embeddings that can be well clustered, facilitating model explanability.

arXiv:2209.00446

Self-Supervised Pretraining of Graph Neural Network for the Retrieval of Related Mathematical Expressions in Scientific Articles

Given the increase of publications, search for relevant papers becomes tedious. In particular, search across disciplines or schools of thinking is not supported. This is mainly due to the retrieval with keyword queries: technical terms differ in different sciences or at different times. Relevant articles might better be identified by their mathematical problem descriptions. Just looking at the equations in a paper already gives a hint to whether the paper is relevant. Hence, we propose a new approach for retrieval of mathematical expressions based on machine learning. We design an unsupervised representation learning task that combines embedding learning with self-supervised learning. Using graph convolutional neural networks we embed mathematical expression into low-dimensional vector spaces that allow efficient nearest neighbor queries. To train our models, we collect a huge dataset with over 29 million mathematical expressions from over 900,000 publications published on arXiv.org. The math is converted into an XML format, which we view as graph data. Our empirical evaluations involving a new dataset of manually annotated search queries show the benefits of using embedding models for mathematical retrieval. This work was originally published at KDD 2020.

arXiv:2209.00078공식 코드 · Papers with Code

Supervised Contrastive Learning with Hard Negative Samples

Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close to each other while pushing negative samples far apart in the embedding space. The positive samples are typically created using "label-preserving" augmentations, i.e., domain-specific transformations of a given datum or anchor. In absence of class information, in unsupervised CL (UCL), the negative samples are typically chosen randomly and independently of the anchor from a preset negative sampling distribution over the entire dataset. This leads to class-collisions in UCL. Supervised CL (SCL), avoids this class collision by conditioning the negative sampling distribution to samples having labels different from that of the anchor. In hard-UCL (H-UCL), which has been shown to be an effective method to further enhance UCL, the negative sampling distribution is conditionally tilted, by means of a hardening function, towards samples that are closer to the anchor. Motivated by this, in this paper we propose hard-SCL (H-SCL) {wherein} the class conditional negative sampling distribution {is tilted} via a hardening function. Our simulation results confirm the utility of H-SCL over SCL with significant performance gains {in downstream classification tasks.} Analytically, we show that {in the} limit of infinite negative samples per anchor and a suitable assumption, the {H-SCL loss} is upper bounded by the {H-UCL loss}, thereby justifying the utility of H-UCL {for controlling} the H-SCL loss in the absence of label information. Through experiments on several datasets, we verify the assumption as well as the claimed inequality between H-UCL and H-SCL losses. We also provide a plausible scenario where H-SCL loss is lower bounded by UCL loss, indicating the limited utility of UCL in controlling the H-SCL loss.

arXiv:2209.00005

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning

Deep Neural Networks (DNNs) have achieved excellent performance in various fields. However, DNNs' vulnerability to Adversarial Examples (AE) hinders their deployments to safety-critical applications. This paper presents a novel AE detection framework, named BEYOND, for trustworthy predictions. BEYOND performs the detection by distinguishing the AE's abnormal relation with its augmented versions, i.e. neighbors, from two prospects: representation similarity and label consistency. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label for its highly informative representation capacity compared to supervised learning models. For clean samples, their representations and predictions are closely consistent with their neighbors, whereas those of AEs differ greatly. Furthermore, we explain this observation and show that by leveraging this discrepancy BEYOND can effectively detect AEs. We develop a rigorous justification for the effectiveness of BEYOND. Furthermore, as a plug-and-play model, BEYOND can easily cooperate with the Adversarial Trained Classifier (ATC), achieving the state-of-the-art (SOTA) robustness accuracy. Experimental results show that BEYOND outperforms baselines by a large margin, especially under adaptive attacks. Empowered by the robust relation net built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed. Our code will be publicly available.

arXiv:2209.00314공식 코드 · Papers with Code

Self-Supervised Pretraining for 2D Medical Image Segmentation

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is scarce or expensive. Self-supervised learning offers a way to lower the need for manually annotated data by pretraining models for a specific domain on unlabelled data. In this approach, labelled data are solely required to fine-tune models for downstream tasks. Medical image segmentation is a field where labelling data requires expert knowledge and collecting large labelled datasets is challenging; therefore, self-supervised learning algorithms promise substantial improvements in this field. Despite this, self-supervised learning algorithms are used rarely to pretrain medical image segmentation networks. In this paper, we elaborate and analyse the effectiveness of supervised and self-supervised pretraining approaches on downstream medical image segmentation, focusing on convergence and data efficiency. We find that self-supervised pretraining on natural images and target-domain-specific images leads to the fastest and most stable downstream convergence. In our experiments on the ACDC cardiac segmentation dataset, this pretraining approach achieves 4-5 times faster fine-tuning convergence compared to an ImageNet pretrained model. We also show that this approach requires less than five epochs of pretraining on domain-specific data to achieve such improvement in the downstream convergence time. Finally, we find that, in low-data scenarios, supervised ImageNet pretraining achieves the best accuracy, requiring less than 100 annotated samples to realise close to minimal error.

arXiv:2208.14845

Listen2YourHeart: A Self-Supervised Approach for Detecting Murmur in Heart-Beat Sounds

Heart murmurs are abnormal sounds present in heartbeats, caused by turbulent blood flow through the heart. The PhysioNet 2022 challenge targets automatic detection of murmur from audio recordings of the heart and automatic detection of normal vs. abnormal clinical outcome. The recordings are captured from multiple locations around the heart. Our participation investigates the effectiveness of selfsupervised learning for murmur detection. We train the layers of a backbone CNN in a self-supervised way with data from both this year's and the 2016 challenge. We use two different augmentations on each training sample, and normalized temperature-scaled cross-entropy loss. We experiment with different augmentations to learn effective phonocardiogram representations. To build the final detectors we train two classification heads, one for each challenge task. We present evaluation results for all combinations of the available augmentations, and for our multipleaugmentation approach. Our team's, Listen2YourHeart, SSL murmur detection classifier received a weighted accuracy score of 0.737 (ranked 13th out of 40 teams) and an outcome identification challenge cost score of 11946 (ranked 7th out of 39 teams) on the hidden test set.

arXiv:2208.14888

Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices. Some recently developed approaches do not require source images during adaptation, but they show limited performance on perturbed images. To address these problems, we propose a novel source-free UDA method that uses only a pre-trained source model and unlabeled target images. Our method captures the aleatoric uncertainty by incorporating data augmentation and trains the feature generator with two consistency objectives. The feature generator is encouraged to learn consistent visual features away from the decision boundaries of the head classifier. Thus, the adapted model becomes more robust to image perturbations. Inspired by self-supervised learning, our method promotes inter-space alignment between the prediction space and the feature space while incorporating intra-space consistency within the feature space to reduce the domain gap between the source and target domains. We also consider epistemic uncertainty to boost the model adaptation performance. Extensive experiments on popular UDA benchmark datasets demonstrate that the proposed source-free method is comparable or even superior to vanilla UDA methods. Moreover, the adapted models show more robust results when input images are perturbed.

arXiv:2208.14073

A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

Representation learning on temporal graphs has drawn considerable research attention owing to its fundamental importance in a wide spectrum of real-world applications. Though a number of studies succeed in obtaining time-dependent representations, it still faces significant challenges. On the one hand, most of the existing methods restrict the embedding space with a certain curvature. However, the underlying geometry in fact shifts among the positive curvature hyperspherical, zero curvature Euclidean and negative curvature hyperbolic spaces in the evolvement over time. On the other hand, these methods usually require abundant labels to learn temporal representations, and thereby notably limit their wide use in the unlabeled graphs of the real applications. To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces. In this paper, we present a novel self-supervised Riemannian graph neural network (SelfRGNN). Specifically, we design a curvature-varying Riemannian GNN with a theoretically grounded time encoding, and formulate a functional curvature over time to model the evolvement shifting among the positive, zero and negative curvature spaces. To enable the self-supervised learning, we propose a novel reweighting self-contrastive approach, exploring the Riemannian space itself without augmentation, and propose an edge-based self-supervised curvature learning with the Ricci curvature. Extensive experiments show the superiority of SelfRGNN, and moreover, the case study shows the time-varying curvature of temporal graph in reality.

arXiv:2208.14022

Stabilize, Decompose, and Denoise: Self-Supervised Fluoroscopy Denoising

Fluoroscopy is an imaging technique that uses X-ray to obtain a real-time 2D video of the interior of a 3D object, helping surgeons to observe pathological structures and tissue functions especially during intervention. However, it suffers from heavy noise that mainly arises from the clinical use of a low dose X-ray, thereby necessitating the technology of fluoroscopy denoising. Such denoising is challenged by the relative motion between the object being imaged and the X-ray imaging system. We tackle this challenge by proposing a self-supervised, three-stage framework that exploits the domain knowledge of fluoroscopy imaging. (i) Stabilize: we first construct a dynamic panorama based on optical flow calculation to stabilize the non-stationary background induced by the motion of the X-ray detector. (ii) Decompose: we then propose a novel mask-based Robust Principle Component Analysis (RPCA) decomposition method to separate a video with detector motion into a low-rank background and a sparse foreground. Such a decomposition accommodates the reading habit of experts. (iii) Denoise: we finally denoise the background and foreground separately by a self-supervised learning strategy and fuse the denoised parts into the final output via a bilateral, spatiotemporal filter. To assess the effectiveness of our work, we curate a dedicated fluoroscopy dataset of 27 videos (1,568 frames) and corresponding ground truth. Our experiments demonstrate that it achieves significant improvements in terms of denoising and enhancement effects when compared with standard approaches. Finally, expert rating confirms this efficacy.

arXiv:2208.13923

SB-SSL: Slice-Based Self-Supervised Transformers for Knee Abnormality Classification from MRI

The availability of large scale data with high quality ground truth labels is a challenge when developing supervised machine learning solutions for healthcare domain. Although, the amount of digital data in clinical workflows is increasing, most of this data is distributed on clinical sites and protected to ensure patient privacy. Radiological readings and dealing with large-scale clinical data puts a significant burden on the available resources, and this is where machine learning and artificial intelligence play a pivotal role. Magnetic Resonance Imaging (MRI) for musculoskeletal (MSK) diagnosis is one example where the scans have a wealth of information, but require a significant amount of time for reading and labeling. Self-supervised learning (SSL) can be a solution for handling the lack of availability of ground truth labels, but generally requires a large amount of training data during the pretraining stage. Herein, we propose a slice-based self-supervised deep learning framework (SB-SSL), a novel slice-based paradigm for classifying abnormality using knee MRI scans. We show that for a limited number of cases (<1000), our proposed framework is capable to identify anterior cruciate ligament tear with an accuracy of 89.17% and an AUC of 0.954, outperforming state-of-the-art without usage of external data during pretraining. This demonstrates that our proposed framework is suited for SSL in the limited data regime.

arXiv:2208.14439공식 코드 · Papers with Code

Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond

While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing SSL methods might not sufficiently describe and associate the above representations within and across image scales. In this paper, we propose a Self-Supervised Pyramid Representation Learning (SS-PRL) framework. The proposed SS-PRL is designed to derive pyramid representations at patch levels via learning proper prototypes, with additional learners to observe and relate inherent semantic information within an image. In particular, we present a cross-scale patch-level correlation learning in SS-PRL, which allows the model to aggregate and associate information learned across patch scales. We show that, with our proposed SS-PRL for model pre-training, one can easily adapt and fine-tune the models for a variety of applications including multi-label classification, object detection, and instance segmentation.