PyTorchKR Papers

최신 논문

총 4,806편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2309.11955

A Study of Forward-Forward Algorithm for Self-Supervised Learning

Self-supervised representation learning has seen remarkable progress in the last few years, with some of the recent methods being able to learn useful image representations without labels. These methods are trained using backpropagation, the de facto standard. Recently, Geoffrey Hinton proposed the forward-forward algorithm as an alternative training method. It utilizes two forward passes and a separate loss function for each layer to train the network without backpropagation. In this study, for the first time, we study the performance of forward-forward vs. backpropagation for self-supervised representation learning and provide insights into the learned representation spaces. Our benchmark employs four standard datasets, namely MNIST, F-MNIST, SVHN and CIFAR-10, and three commonly used self-supervised representation learning techniques, namely rotation, flip and jigsaw. Our main finding is that while the forward-forward algorithm performs comparably to backpropagation during (self-)supervised training, the transfer performance is significantly lagging behind in all the studied settings. This may be caused by a combination of factors, including having a loss function for each layer and the way the supervised training is realized in the forward-forward paradigm. In comparison to backpropagation, the forward-forward algorithm focuses more on the boundaries and drops part of the information unnecessary for making decisions which harms the representation learning goal. Further investigation and research are necessary to stabilize the forward-forward strategy for self-supervised learning, to work beyond the datasets and configurations demonstrated by Geoffrey Hinton.

arXiv:2309.11711공식 코드 · Papers with Code

MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unlabeled video frames. Drawing upon recent advancements of self-supervised learning of the object motion from unlabeled videos with geometric constraint, we design a \textbf{Mo}tion-guided \textbf{D}omain \textbf{A}daptive semantic segmentation framework (MoDA). MoDA harnesses the self-supervised object motion cues to facilitate cross-domain alignment for segmentation task. First, we present an object discovery module to localize and segment target moving objects using object motion information. Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain. Subsequently, these high-quality pseudo labels are used in the self-training loop to bridge the cross-domain gap. On domain adaptive video and image segmentation experiments, MoDA shows the effectiveness utilizing object motion as guidance for domain alignment compared with optical flow information. Moreover, MoDA exhibits versatility as it can complement existing state-of-the-art UDA approaches. Code at https://github.com/feipanir/MoDA.

arXiv:2309.11782

DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning

Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance with high improvement potential, prompting researchers to enhance these frameworks further. Assimilating CL into non-CL frameworks has been thought to be beneficial, but empirical evidence indicates no visible improvements. In view of that, this paper proposes a strategy of performing CL along the dimensional direction instead of along the batch direction as done in conventional contrastive learning, named Dimensional Contrastive Learning (DimCL). DimCL aims to enhance the feature diversity, and it can serve as a regularizer to prior SSL frameworks. DimCL has been found to be effective, and the hardness-aware property is identified as a critical reason for its success. Extensive experimental results reveal that assimilating DimCL into SSL frameworks leads to performance improvement by a non-trivial margin on various datasets and backbone architectures.

arXiv:2309.11354공식 코드 · Papers with Code

Self-supervised learning unveils change in urban housing from street-level images

Cities around the world face a critical shortage of affordable and decent housing. Despite its critical importance for policy, our ability to effectively monitor and track progress in urban housing is limited. Deep learning-based computer vision methods applied to street-level images have been successful in the measurement of socioeconomic and environmental inequalities but did not fully utilize temporal images to track urban change as time-varying labels are often unavailable. We used self-supervised methods to measure change in London using 15 million street images taken between 2008 and 2021. Our novel adaptation of Barlow Twins, Street2Vec, embeds urban structure while being invariant to seasonal and daily changes without manual annotations. It outperformed generic embeddings, successfully identified point-level change in London's housing supply from street-level images, and distinguished between major and minor change. This capability can provide timely information for urban planning and policy decisions toward more liveable, equitable, and sustainable cities.

arXiv:2309.10147공식 코드 · Papers with Code

Realistic Website Fingerprinting By Augmenting Network Trace

Website Fingerprinting (WF) is considered a major threat to the anonymity of Tor users (and other anonymity systems). While state-of-the-art WF techniques have claimed high attack accuracies, e.g., by leveraging Deep Neural Networks (DNN), several recent works have questioned the practicality of such WF attacks in the real world due to the assumptions made in the design and evaluation of these attacks. In this work, we argue that such impracticality issues are mainly due to the attacker's inability in collecting training data in comprehensive network conditions, e.g., a WF classifier may be trained only on samples collected on specific high-bandwidth network links but deployed on connections with different network conditions. We show that augmenting network traces can enhance the performance of WF classifiers in unobserved network conditions. Specifically, we introduce NetAugment, an augmentation technique tailored to the specifications of Tor traces. We instantiate NetAugment through semi-supervised and self-supervised learning techniques. Our extensive open-world and close-world experiments demonstrate that under practical evaluation settings, our WF attacks provide superior performances compared to the state-of-the-art; this is due to their use of augmented network traces for training, which allows them to learn the features of target traffic in unobserved settings. For instance, with a 5-shot learning in a closed-world scenario, our self-supervised WF attack (named NetCLR) reaches up to 80% accuracy when the traces for evaluation are collected in a setting unobserved by the WF adversary. This is compared to an accuracy of 64.4% achieved by the state-of-the-art Triplet Fingerprinting [35]. We believe that the promising results of our work can encourage the use of network trace augmentation in other types of network traffic analysis.

arXiv:2309.09548

Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata

Automated speech intelligibility assessment is pivotal for hearing aid (HA) development. In this paper, we present three novel methods to improve intelligibility prediction accuracy and introduce MBI-Net+, an enhanced version of MBI-Net, the top-performing system in the 1st Clarity Prediction Challenge. MBI-Net+ leverages Whisper's embeddings to create cross-domain acoustic features and includes metadata from speech signals by using a classifier that distinguishes different enhancement methods. Furthermore, MBI-Net+ integrates the hearing-aid speech perception index (HASPI) as a supplementary metric into the objective function to further boost prediction performance. Experimental results demonstrate that MBI-Net+ surpasses several intrusive baseline systems and MBI-Net on the Clarity Prediction Challenge 2023 dataset, validating the effectiveness of incorporating Whisper embeddings, speech metadata, and related complementary metrics to improve prediction performance for HA.

arXiv:2309.09563

RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy

Unlike in natural images, in endoscopy there is no clear notion of an up-right camera orientation. Endoscopic videos therefore often contain large rotational motions, which require keypoint detection and description algorithms to be robust to these conditions. While most classical methods achieve rotation-equivariant detection and invariant description by design, many learning-based approaches learn to be robust only up to a certain degree. At the same time learning-based methods under moderate rotations often outperform classical approaches. In order to address this shortcoming, in this paper we propose RIDE, a learning-based method for rotation-equivariant detection and invariant description. Following recent advancements in group-equivariant learning, RIDE models rotation-equivariance implicitly within its architecture. Trained in a self-supervised manner on a large curation of endoscopic images, RIDE requires no manual labeling of training data. We test RIDE in the context of surgical tissue tracking on the SuPeR dataset as well as in the context of relative pose estimation on a repurposed version of the SCARED dataset. In addition we perform explicit studies showing its robustness to large rotations. Our comparison against recent learning-based and classical approaches shows that RIDE sets a new state-of-the-art performance on matching and relative pose estimation tasks and scores competitively on surgical tissue tracking.

arXiv:2309.09490

Self-supervised TransUNet for Ultrasound regional segmentation of the distal radius in children

Supervised deep learning offers great promise to automate analysis of medical images from segmentation to diagnosis. However, their performance highly relies on the quality and quantity of the data annotation. Meanwhile, curating large annotated datasets for medical images requires a high level of expertise, which is time-consuming and expensive. Recently, to quench the thirst for large data sets with high-quality annotation, self-supervised learning (SSL) methods using unlabeled domain-specific data, have attracted attention. Therefore, designing an SSL method that relies on minimal quantities of labeled data has far-reaching significance in medical images. This paper investigates the feasibility of deploying the Masked Autoencoder for SSL (SSL-MAE) of TransUNet, for segmenting bony regions from children's wrist ultrasound scans. We found that changing the embedding and loss function in SSL-MAE can produce better downstream results compared to the original SSL-MAE. In addition, we determined that only pretraining TransUNet embedding and encoder with SSL-MAE does not work as well as TransUNet without SSL-MAE pretraining on downstream segmentation tasks.

arXiv:2309.09473

Self-supervised Multi-view Clustering in Computer Vision: A Survey

Multi-view clustering (MVC) has had significant implications in cross-modal representation learning and data-driven decision-making in recent years. It accomplishes this by leveraging the consistency and complementary information among multiple views to cluster samples into distinct groups. However, as contrastive learning continues to evolve within the field of computer vision, self-supervised learning has also made substantial research progress and is progressively becoming dominant in MVC methods. It guides the clustering process by designing proxy tasks to mine the representation of image and video data itself as supervisory information. Despite the rapid development of self-supervised MVC, there has yet to be a comprehensive survey to analyze and summarize the current state of research progress. Therefore, this paper explores the reasons and advantages of the emergence of self-supervised MVC and discusses the internal connections and classifications of common datasets, data issues, representation learning methods, and self-supervised learning methods. This paper does not only introduce the mechanisms for each category of methods but also gives a few examples of how these techniques are used. In the end, some open problems are pointed out for further investigation and development.

arXiv:2309.09446공식 코드 · Papers with Code

Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised Learning

Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning. The availability of robust Geographic Information System (GIS) layers can benefit the management of infrastructure inventories, especially at local government level with urban planners responsible for the deployment and maintenance of such infrastructure. However, many cities still lack real-time information on the location, connectivity, and width of footpaths, and/or employ costly and manual survey means to gather this information. This work designs and implements an automatic pipeline for generating footpath networks based on remote sensing images using machine learning models. The annotation of segmentation tasks, especially labeling remote sensing images with specialized requirements, is very expensive, so we aim to introduce a pipeline requiring less labeled data. Considering supervised methods require large amounts of training data, we use a self-supervised method for feature representation learning to reduce annotation requirements. Then the pre-trained model is used as the encoder of the U-Net for footpath segmentation. Based on the generated masks, the footpath polygons are extracted and converted to footpath networks which can be loaded and visualized by geographic information systems conveniently. Validation results indicate considerable consistency when compared to manually collected GIS layers. The footpath network generation pipeline proposed in this work is low-cost and extensible, and it can be applied where remote sensing images are available. Github: https://github.com/WennyXY/FootpathSeg.

arXiv:2309.08744

Personalized Food Image Classification: Benchmark Datasets and New Baseline

Food image classification is a fundamental step of image-based dietary assessment, enabling automated nutrient analysis from food images. Many current methods employ deep neural networks to train on generic food image datasets that do not reflect the dynamism of real-life food consumption patterns, in which food images appear sequentially over time, reflecting the progression of what an individual consumes. Personalized food classification aims to address this problem by training a deep neural network using food images that reflect the consumption pattern of each individual. However, this problem is under-explored and there is a lack of benchmark datasets with individualized food consumption patterns due to the difficulty in data collection. In this work, we first introduce two benchmark personalized datasets including the Food101-Personal, which is created based on surveys of daily dietary patterns from participants in the real world, and the VFNPersonal, which is developed based on a dietary study. In addition, we propose a new framework for personalized food image classification by leveraging self-supervised learning and temporal image feature information. Our method is evaluated on both benchmark datasets and shows improved performance compared to existing works. The dataset has been made available at: https://skynet.ecn.purdue.edu/~pan161/dataset_personal.html

arXiv:2309.09220

Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables

The performance of deep learning models depends significantly on their capacity to encode input features efficiently and decode them into meaningful outputs. Better input and output representation has the potential to boost models' performance and generalization. In the context of acoustic-to-articulatory speech inversion (SI) systems, we study the impact of utilizing speech representations acquired via self-supervised learning (SSL) models, such as HuBERT compared to conventional acoustic features. Additionally, we investigate the incorporation of novel tract variables (TVs) through an improved geometric transformation model. By combining these two approaches, we improve the Pearson product-moment correlation (PPMC) scores which evaluate the accuracy of TV estimation of the SI system from 0.7452 to 0.8141, a 6.9% increase. Our findings underscore the profound influence of rich feature representations from SSL models and improved geometric transformations with target TVs on the enhanced functionality of SI systems.

arXiv:2309.08374

Understanding the limitations of self-supervised learning for tabular anomaly detection

While self-supervised learning has improved anomaly detection in computer vision and natural language processing, it is unclear whether tabular data can benefit from it. This paper explores the limitations of self-supervision for tabular anomaly detection. We conduct several experiments spanning various pretext tasks on 26 benchmark datasets to understand why this is the case. Our results confirm representations derived from self-supervision do not improve tabular anomaly detection performance compared to using the raw representations of the data. We show this is due to neural networks introducing irrelevant features, which reduces the effectiveness of anomaly detectors. However, we demonstrate that using a subspace of the neural network's representation can recover performance.

arXiv:2309.08153공식 코드 · Papers with Code

Fine-tune the pretrained ATST model for sound event detection

Sound event detection (SED) often suffers from the data deficiency problem. The recent baseline system in the DCASE2023 challenge task 4 leverages the large pretrained self-supervised learning (SelfSL) models to mitigate such restriction, where the pretrained models help to produce more discriminative features for SED. However, the pretrained models are regarded as a frozen feature extractor in the challenge baseline system and most of the challenge submissions, and fine-tuning of the pretrained models has been rarely studied. In this work, we study the fine-tuning method of the pretrained models for SED. We first introduce ATST-Frame, our newly proposed SelfSL model, to the SED system. ATST-Frame was especially designed for learning frame-level representations of audio signals and obtained state-of-the-art (SOTA) performances on a series of downstream tasks. We then propose a fine-tuning method for ATST-Frame using both (in-domain) unlabelled and labelled SED data. Our experiments show that, the proposed method overcomes the overfitting problem when fine-tuning the large pretrained network, and our SED system obtains new SOTA results of 0.587/0.812 PSDS1/PSDS2 scores on the DCASE challenge task 4 dataset.

arXiv:2309.07498

Hierarchical Metadata Information Constrained Self-Supervised Learning for Anomalous Sound Detection Under Domain Shift

Self-supervised learning methods have achieved promising performance for anomalous sound detection (ASD) under domain shift, where the type of domain shift is considered in feature learning by incorporating section IDs. However, the attributes accompanying audio files under each section, such as machine operating conditions and noise types, have not been considered, although they are also crucial for characterizing domain shifts. In this paper, we present a hierarchical metadata information constrained self-supervised (HMIC) ASD method, where the hierarchical relation between section IDs and attributes is constructed, and used as constraints to obtain finer feature representation. In addition, we propose an attribute-group-center (AGC)-based method for calculating the anomaly score under the domain shift condition. Experiments are performed to demonstrate its improved performance over the state-of-the-art self-supervised methods in DCASE 2022 challenge Task 2.

arXiv:2309.07377공식 코드 · Papers with Code

Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ natural language processing techniques. However, these studies, mainly single-task focused, faced challenges like overfitting and performance degradation in speech recognition tasks, often at the cost of sacrificing performance in multi-task scenarios. This study presents a comprehensive comparison and optimization of discrete tokens generated by various leading SSL models in speech recognition and synthesis tasks. We aim to explore the universality of speech discrete tokens across multiple speech tasks. Experimental results demonstrate that discrete tokens achieve comparable results against systems trained on FBank features in speech recognition tasks and outperform mel-spectrogram features in speech synthesis in subjective and objective metrics. These findings suggest that universal discrete tokens have enormous potential in various speech-related tasks. Our work is open-source and publicly available at https://github.com/k2-fsa/icefall.

arXiv:2309.07287

Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis

The assessment of children at risk of autism typically involves a clinician observing, taking notes, and rating children's behaviors. A machine learning model that can label adult and child audio may largely save labor in coding children's behaviors, helping clinicians capture critical events and better communicate with parents. In this study, we leverage Wav2Vec 2.0 (W2V2), pre-trained on 4300-hour of home audio of children under 5 years old, to build a unified system for tasks of clinician-child speaker diarization and vocalization classification (VC). To enhance children's VC, we build a W2V2 phoneme recognition system for children under 4 years old, and we incorporate its phonetically-tuned embeddings as auxiliary features or recognize pseudo phonetic transcripts as an auxiliary task. We test our method on two corpora (Rapid-ABC and BabbleCor) and obtain consistent improvements. Additionally, we outperform the state-of-the-art performance on the reproducible subset of BabbleCor. Code available at https://huggingface.co/lijialudew

arXiv:2309.07145

ETP: Learning Transferable ECG Representations via ECG-Text Pre-training

In the domain of cardiovascular healthcare, the Electrocardiogram (ECG) serves as a critical, non-invasive diagnostic tool. Although recent strides in self-supervised learning (SSL) have been promising for ECG representation learning, these techniques often require annotated samples and struggle with classes not present in the fine-tuning stages. To address these limitations, we introduce ECG-Text Pre-training (ETP), an innovative framework designed to learn cross-modal representations that link ECG signals with textual reports. For the first time, this framework leverages the zero-shot classification task in the ECG domain. ETP employs an ECG encoder along with a pre-trained language model to align ECG signals with their corresponding textual reports. The proposed framework excels in both linear evaluation and zero-shot classification tasks, as demonstrated on the PTB-XL and CPSC2018 datasets, showcasing its ability for robust and generalizable cross-modal ECG feature learning.

arXiv:2309.07778공식 코드 · Papers with Code

Virchow: A Million-Slide Digital Pathology Foundation Model

The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnosis and treatment of cancer. Such applications will depend on models' abilities to capture the diverse patterns observed in pathology images. To address this challenge, we present Virchow, a foundation model for computational pathology. Using self-supervised learning empowered by the DINOv2 algorithm, Virchow is a vision transformer model with 632 million parameters trained on 1.5 million hematoxylin and eosin stained whole slide images from diverse tissue and specimen types, which is orders of magnitude more data than previous works. The Virchow model enables the development of a pan-cancer detection system with 0.949 overall specimen-level AUC across 17 different cancer types, while also achieving 0.937 AUC on 7 rare cancer types. The Virchow model sets the state-of-the-art on the internal and external image tile level benchmarks and slide level biomarker prediction tasks. The gains in performance highlight the importance of training on massive pathology image datasets, suggesting scaling up the data and network architecture can improve the accuracy for many high-impact computational pathology applications where limited amounts of training data are available.

arXiv:2309.07526

Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning

By identifying similarities between successive inputs, Self-Supervised Learning (SSL) methods for time series analysis have demonstrated their effectiveness in encoding the inherent static characteristics of temporal data. However, an exclusive emphasis on similarities might result in representations that overlook the dynamic attributes critical for modeling cardiovascular diseases within a confined subject cohort. Introducing Distilled Encoding Beyond Similarities (DEBS), this paper pioneers an SSL approach that transcends mere similarities by integrating dissimilarities among positive pairs. The framework is applied to electrocardiogram (ECG) signals, leading to a notable enhancement of +10\% in the detection accuracy of Atrial Fibrillation (AFib) across diverse subjects. DEBS underscores the potential of attaining a more refined representation by encoding the dynamic characteristics of time series data, tapping into dissimilarities during the optimization process. Broadly, the strategy delineated in this study holds the promise of unearthing novel avenues for advancing SSL methodologies tailored to temporal data.