PyTorchKR Papers

최신 논문

총 4,806편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.19579

The Bad Batches: Enhancing Self-Supervised Learning in Image Classification Through Representative Batch Curation

The pursuit of learning robust representations without human supervision is a longstanding challenge. The recent advancements in self-supervised contrastive learning approaches have demonstrated high performance across various representation learning challenges. However, current methods depend on the random transformation of training examples, resulting in some cases of unrepresentative positive pairs that can have a large impact on learning. This limitation not only impedes the convergence of the learning process but the robustness of the learnt representation as well as requiring larger batch sizes to improve robustness to such bad batches. This paper attempts to alleviate the influence of false positive and false negative pairs by employing pairwise similarity calculations through the Fr\'echet ResNet Distance (FRD), thereby obtaining robust representations from unlabelled data. The effectiveness of the proposed method is substantiated by empirical results, where a linear classifier trained on self-supervised contrastive representations achieved an impressive 87.74\% top-1 accuracy on STL10 and 99.31\% on the Flower102 dataset. These results emphasize the potential of the proposed approach in pushing the boundaries of the state-of-the-art in self-supervised contrastive learning, particularly for image classification tasks.

arXiv:2403.19111

Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection

Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by generating high-resolution frames, they often lack competence in preserving detailed spatial and temporal coherence in video frames. To tackle this issue, we propose a self-supervised learning approach for VAD through an inter-patch relationship prediction task. Specifically, we introduce a two-branch vision transformer network designed to capture deep visual features of video frames, addressing spatial and temporal dimensions responsible for modeling appearance and motion patterns, respectively. The inter-patch relationship in each dimension is decoupled into inter-patch similarity and the order information of each patch. To mitigate memory consumption, we convert the order information prediction task into a multi-label learning problem, and the inter-patch similarity prediction task into a distance matrix regression problem. Comprehensive experiments demonstrate the effectiveness of our method, surpassing pixel-generation-based methods by a significant margin across three public benchmarks. Additionally, our approach outperforms other self-supervised learning-based methods.

arXiv:2403.19078

MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck

Self-supervised learning aims to learn representation that can be effectively generalized to downstream tasks. Many self-supervised approaches regard two views of an image as both the input and the self-supervised signals, assuming that either view contains the same task-relevant information and the shared information is (approximately) sufficient for predicting downstream tasks. Recent studies show that discarding superfluous information not shared between the views can improve generalization. Hence, the ideal representation is sufficient for downstream tasks and contains minimal superfluous information, termed minimal sufficient representation. One can learn this representation by maximizing the mutual information between the representation and the supervised view while eliminating superfluous information. Nevertheless, the computation of mutual information is notoriously intractable. In this work, we propose an objective termed multi-view entropy bottleneck (MVEB) to learn minimal sufficient representation effectively. MVEB simplifies the minimal sufficient learning to maximizing both the agreement between the embeddings of two views and the differential entropy of the embedding distribution. Our experiments confirm that MVEB significantly improves performance. For example, it achieves top-1 accuracy of 76.9\% on ImageNet with a vanilla ResNet-50 backbone on linear evaluation. To the best of our knowledge, this is the new state-of-the-art result with ResNet-50.

arXiv:2403.18560공식 코드 · Papers with Code

Noise-Robust Keyword Spotting through Self-supervised Pretraining

Voice assistants are now widely available, and to activate them a keyword spotting (KWS) algorithm is used. Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a good performance. Leveraging unlabelled data through self-supervised learning (SSL) has been shown to increase the accuracy in clean conditions. This paper explores how SSL pretraining such as Data2Vec can be used to enhance the robustness of KWS models in noisy conditions, which is under-explored. Models of three different sizes are pretrained using different pretraining approaches and then fine-tuned for KWS. These models are then tested and compared to models trained using two baseline supervised learning methods, one being standard training using clean data and the other one being multi-style training (MTR). The results show that pretraining and fine-tuning on clean data is superior to supervised learning on clean data across all testing conditions, and superior to supervised MTR for testing conditions of SNR above 5 dB. This indicates that pretraining alone can increase the model's robustness. Finally, it is found that using noisy data for pretraining models, especially with the Data2Vec-denoising approach, significantly enhances the robustness of KWS models in noisy conditions.

arXiv:2403.18361

ViTAR: Vision Transformer with Any Resolution

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from those seen during training. Our work introduces two key innovations to address this issue. Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration. Secondly, we introduce fuzzy positional encoding in the Vision Transformer to provide consistent positional awareness across multiple resolutions, thereby preventing overfitting to any single training resolution. Our resulting model, ViTAR (Vision Transformer with Any Resolution), demonstrates impressive adaptability, achieving 83.3\% top-1 accuracy at a 1120x1120 resolution and 80.4\% accuracy at a 4032x4032 resolution, all while reducing computational costs. ViTAR also shows strong performance in downstream tasks such as instance and semantic segmentation and can easily combined with self-supervised learning techniques like Masked AutoEncoder. Our work provides a cost-effective solution for enhancing the resolution scalability of ViTs, paving the way for more versatile and efficient high-resolution image processing.

arXiv:2403.18266

Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning

Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data. However, as real-world applications continually integrate new content, the high computational and resource demands of SSL necessitate continual learning rather than complete retraining. This poses a challenge in striking a balance between stability and plasticity when adapting to new information. In this paper, we employ Centered Kernel Alignment for quantitatively analyzing model stability and plasticity, revealing the critical roles of batch normalization layers for stability and convolutional layers for plasticity. Motivated by this, we propose Branch-tuning, an efficient and straightforward method that achieves a balance between stability and plasticity in continual SSL. Branch-tuning consists of branch expansion and compression, and can be easily applied to various SSL methods without the need of modifying the original methods, retaining old data or models. We validate our method through incremental experiments on various benchmark datasets, demonstrating its effectiveness and practical value in real-world scenarios. We hope our work offers new insights for future continual self-supervised learning research. The code will be made publicly available.

arXiv:2403.17231

Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination

This paper presents a self-supervised learning method to safely learn a motion planner for ground robots to navigate environments with dense and dynamic obstacles. When facing highly-cluttered, fast-moving, hard-to-predict obstacles, classical motion planners may not be able to keep up with limited onboard computation. For learning-based planners, high-quality demonstrations are difficult to acquire for imitation learning while reinforcement learning becomes inefficient due to the high probability of collision during exploration. To safely and efficiently provide training data, the Learning from Hallucination (LfH) approaches synthesize difficult navigation environments based on past successful navigation experiences in relatively easy or completely open ones, but unfortunately cannot address dynamic obstacles. In our new Dynamic Learning from Learned Hallucination (Dyna-LfLH), we design and learn a novel latent distribution and sample dynamic obstacles from it, so the generated training data can be used to learn a motion planner to navigate in dynamic environments. Dyna-LfLH is evaluated on a ground robot in both simulated and physical environments and achieves up to 25% better success rate compared to baselines.

arXiv:2403.17728공식 코드 · Papers with Code

Masked Autoencoders are PDE Learners

Neural solvers for partial differential equations (PDEs) have great potential to generate fast and accurate physics solutions, yet their practicality is currently limited by their generalizability. PDEs evolve over broad scales and exhibit diverse behaviors; predicting these phenomena will require learning representations across a wide variety of inputs which may encompass different coefficients, boundary conditions, resolutions, or even equations. As a step towards generalizable PDE modeling, we adapt masked pretraining for physics problems. Through self-supervised learning across PDEs, masked autoencoders can consolidate heterogeneous physics to learn rich latent representations. We show that learned representations can generalize to a limited set of unseen equations or parameters and are meaningful enough to regress PDE coefficients or the classify PDE features. Furthermore, conditioning neural solvers on learned latent representations can improve time-stepping and super-resolution performance across a variety of coefficients, discretizations, or boundary conditions, as well as on certain unseen PDEs. We hope that masked pretraining can emerge as a unifying method across large, unlabeled, and heterogeneous datasets to learn latent physics at scale.

arXiv:2403.17823공식 코드 · Papers with Code

Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders

Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sourced from the same image but cropped differently, deviating from the conventional pairs of frames extracted from a video. CropMAE therefore alleviates the need for video datasets, while maintaining competitive performances and drastically reducing pre-training and learning time. Furthermore, we demonstrate that CropMAE learns similar object-centric representations without explicit motion, showing that current self-supervised learning methods do not learn such representations from explicit object motion, but rather thanks to the implicit image transformations that occur between the two views. Finally, CropMAE achieves the highest masking ratio to date (98.5%), enabling the reconstruction of images using only two visible patches. Our code is available at https://github.com/alexandre-eymael/CropMAE.

arXiv:2403.17530

Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and generalization capabilities of models trained in low-data regimes. Methods: The proposed method starts with a pre-training phase, where features learned in a self-supervised learning setting are disentangled to improve the robustness of the representations for downstream tasks. We then introduce a meta-fine-tuning step, leveraging related classes between meta-training and meta-testing phases but varying the granularity level. This approach aims to enhance the model's generalization capabilities by exposing it to more challenging classification tasks during meta-training and evaluating it on easier tasks but holding greater clinical relevance during meta-testing. We demonstrate the effectiveness of the proposed approach through a series of experiments exploring several backbones, as well as diverse pre-training and fine-tuning schemes, on two distinct medical tasks, i.e., classification of prostate cancer aggressiveness from MRI data and classification of breast cancer malignity from microscopic images. Results: Our results indicate that the proposed approach consistently yields superior performance w.r.t. ablation experiments, maintaining competitiveness even when a distribution shift between training and evaluation data occurs. Conclusion: Extensive experiments demonstrate the effectiveness and wide applicability of the proposed approach. We hope that this work will add another solution to the arsenal of addressing learning issues in data-scarce imaging domains.

arXiv:2403.16974공식 코드 · Papers with Code

Self-STORM: Deep Unrolled Self-Supervised Learning for Super-Resolution Microscopy

The use of fluorescent molecules to create long sequences of low-density, diffraction-limited images enables highly-precise molecule localization. However, this methodology requires lengthy imaging times, which limits the ability to view dynamic interactions of live cells on short time scales. Many techniques have been developed to reduce the number of frames needed for localization, from classic iterative optimization to deep neural networks. Particularly, deep algorithm unrolling utilizes both the structure of iterative sparse recovery algorithms and the performance gains of supervised deep learning. However, the robustness of this approach is highly dependant on having sufficient training data. In this paper we introduce deep unrolled self-supervised learning, which alleviates the need for such data by training a sequence-specific, model-based autoencoder that learns only from given measurements. Our proposed method exceeds the performance of its supervised counterparts, thus allowing for robust, dynamic imaging well below the diffraction limit without any labeled training samples. Furthermore, the suggested model-based autoencoder scheme can be utilized to enhance generalization in any sparse recovery framework, without the need for external training data.

arXiv:2310.03274공식 코드 · Papers with Code

Fragment-based Pretraining and Finetuning on Molecular Graphs

Property prediction on molecular graphs is an important application of Graph Neural Networks. Recently, unlabeled molecular data has become abundant, which facilitates the rapid development of self-supervised learning for GNNs in the chemical domain. In this work, we propose pretraining GNNs at the fragment level, a promising middle ground to overcome the limitations of node-level and graph-level pretraining. Borrowing techniques from recent work on principal subgraph mining, we obtain a compact vocabulary of prevalent fragments from a large pretraining dataset. From the extracted vocabulary, we introduce several fragment-based contrastive and predictive pretraining tasks. The contrastive learning task jointly pretrains two different GNNs: one on molecular graphs and the other on fragment graphs, which represents higher-order connectivity within molecules. By enforcing consistency between the fragment embedding and the aggregated embedding of the corresponding atoms from the molecular graphs, we ensure that the embeddings capture structural information at multiple resolutions. The structural information of fragment graphs is further exploited to extract auxiliary labels for graph-level predictive pretraining. We employ both the pretrained molecular-based and fragment-based GNNs for downstream prediction, thus utilizing the fragment information during finetuning. Our graph fragment-based pretraining (GraphFP) advances the performances on 5 out of 8 common molecular benchmarks and improves the performances on long-range biological benchmarks by at least 11.5%. Code is available at: https://github.com/lvkd84/GraphFP.

arXiv:2403.16265

Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs

We study the patent phrase similarity inference task, which measures the semantic similarity between two patent phrases. As patent documents employ legal and highly technical language, existing semantic textual similarity methods that use localized contextual information do not perform satisfactorily in inferring patent phrase similarity. To address this, we introduce a graph-augmented approach to amplify the global contextual information of the patent phrases. For each patent phrase, we construct a phrase graph that links to its focal patents and a list of patents that are either cited by or cite these focal patents. The augmented phrase embedding is then derived from combining its localized contextual embedding with its global embedding within the phrase graph. We further propose a self-supervised learning objective that capitalizes on the retrieved topology to refine both the contextualized embedding and the graph parameters in an end-to-end manner. Experimental results from a unique patent phrase similarity dataset demonstrate that our approach significantly enhances the representation of patent phrases, resulting in marked improvements in similarity inference in a self-supervised fashion. Substantial improvements are also observed in the supervised setting, underscoring the potential benefits of leveraging retrieved phrase graph augmentation.

arXiv:2403.15790

Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasets

The field of imbalanced self-supervised learning, especially in the context of tabular data, has not been extensively studied. Existing research has predominantly focused on image datasets. This paper aims to fill this gap by examining the specific challenges posed by data imbalance in self-supervised learning in the domain of tabular data, with a primary focus on autoencoders. Autoencoders are widely employed for learning and constructing a new representation of a dataset, particularly for dimensionality reduction. They are also often used for generative model learning, as seen in variational autoencoders. When dealing with mixed tabular data, qualitative variables are often encoded using a one-hot encoder with a standard loss function (MSE or Cross Entropy). In this paper, we analyze the drawbacks of this approach, especially when categorical variables are imbalanced. We propose a novel metric to balance learning: a Multi-Supervised Balanced MSE. This approach reduces the reconstruction error by balancing the influence of variables. Finally, we empirically demonstrate that this new metric, compared to the standard MSE: i) outperforms when the dataset is imbalanced, especially when the learning process is insufficient, and ii) provides similar results in the opposite case.

arXiv:2403.16137공식 코드 · Papers with Code

A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective

Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial to learning generalized representations for GFMs. However, existing surveys of GFMs have several shortcomings: they lack comprehensiveness regarding the most recent progress, have unclear categorization of self-supervised methods, and take a limited architecture-based perspective that is restricted to only certain types of graph models. As the ultimate goal of GFMs is to learn generalized graph knowledge, we provide a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. We propose a knowledge-based taxonomy, which categorizes self-supervised graph models by the specific graph knowledge utilized. Our taxonomy consists of microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic knowledge (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and more than 25 pretext tasks for pre-training GFMs, as well as various downstream task generalization strategies. Such a knowledge-based taxonomy allows us to re-examine graph models based on new architectures more clearly, such as graph language models, as well as provide more in-depth insights for constructing GFMs.

arXiv:2403.15918공식 코드 · Papers with Code

Towards Adversarial Robustness And Backdoor Mitigation in SSL

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world problems. However, SSL methods have recently been shown to be vulnerable to backdoor attacks, where the learned model can be exploited by adversaries to manipulate the learned representations, either through tampering the training data distribution, or via modifying the model itself. This work aims to address defending against backdoor attacks in SSL, where the adversary has access to a realistic fraction of the SSL training data, and no access to the model. We use novel methods that are computationally efficient as well as generalizable across different problem settings. We also investigate the adversarial robustness of SSL models when trained with our method, and show insights into increased robustness in SSL via frequency domain augmentations. We demonstrate the effectiveness of our method on a variety of SSL benchmarks, and show that our method is able to mitigate backdoor attacks while maintaining high performance on downstream tasks. Code for our work is available at github.com/Aryan-Satpathy/Backdoor

arXiv:2403.15693

Technical Report: Masked Skeleton Sequence Modeling for Learning Larval Zebrafish Behavior Latent Embeddings

In this report, we introduce a novel self-supervised learning method for extracting latent embeddings from behaviors of larval zebrafish. Drawing inspiration from Masked Modeling techniquesutilized in image processing with Masked Autoencoders (MAE) \cite{he2022masked} and in natural language processing with Generative Pre-trained Transformer (GPT) \cite{radford2018improving}, we treat behavior sequences as a blend of images and language. For the skeletal sequences of swimming zebrafish, we propose a pioneering Transformer-CNN architecture, the Sequence Spatial-Temporal Transformer (SSTFormer), designed to capture the inter-frame correlation of different joints. This correlation is particularly valuable, as it reflects the coordinated movement of various parts of the fish body across adjacent frames. To handle the high frame rate, we segment the skeleton sequence into distinct time slices, analogous to "words" in a sentence, and employ self-attention transformer layers to encode the consecutive frames within each slice, capturing the spatial correlation among different joints. Furthermore, we incorporate a CNN-based attention module to enhance the representations outputted by the transformer layers. Lastly, we introduce a temporal feature aggregation operation between time slices to improve the discrimination of similar behaviors.

arXiv:2403.16499

Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes

Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.

arXiv:2403.16194공식 코드 · Papers with Code

Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery

Unsupervised landmarks discovery (ULD) for an object category is a challenging computer vision problem. In pursuit of developing a robust ULD framework, we explore the potential of a recent paradigm of self-supervised learning algorithms, known as diffusion models. Some recent works have shown that these models implicitly contain important correspondence cues. Towards harnessing the potential of diffusion models for the ULD task, we make the following core contributions. First, we propose a ZeroShot ULD baseline based on simple clustering of random pixel locations with nearest neighbour matching. It delivers better results than existing ULD methods. Second, motivated by the ZeroShot performance, we develop a ULD algorithm based on diffusion features using self-training and clustering which also outperforms prior methods by notable margins. Third, we introduce a new proxy task based on generating latent pose codes and also propose a two-stage clustering mechanism to facilitate effective pseudo-labeling, resulting in a significant performance improvement. Overall, our approach consistently outperforms state-of-the-art methods on four challenging benchmarks AFLW, MAFL, CatHeads and LS3D by significant margins.

arXiv:2403.16272

L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction

Pre-training strategies based on self-supervised learning (SSL) have proven to be effective pretext tasks for many downstream tasks in computer vision. Due to the significant disparity between medical and natural images, the application of typical SSL is not straightforward in medical imaging. Additionally, those pretext tasks often lack context, which is critical for computer-aided clinical decision support. In this paper, we developed a longitudinal masked auto-encoder (MAE) based on the well-known Transformer-based MAE. In particular, we explored the importance of time-aware position embedding as well as disease progression-aware masking. Taking into account the time between examinations instead of just scheduling them offers the benefit of capturing temporal changes and trends. The masking strategy, for its part, evolves during follow-up to better capture pathological changes, ensuring a more accurate assessment of disease progression. Using OPHDIAT, a large follow-up screening dataset targeting diabetic retinopathy (DR), we evaluated the pre-trained weights on a longitudinal task, which is to predict the severity label of the next visit within 3 years based on the past time series examinations. Our results demonstrated the relevancy of both time-aware position embedding and masking strategies based on disease progression knowledge. Compared to popular baseline models and standard longitudinal Transformers, these simple yet effective extensions significantly enhance the predictive ability of deep classification models.