PyTorchKR Papers

최신 논문

총 5,360편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2302.02055공식 코드 · Papers with Code

Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction

Few-shot learning is a promising approach to molecular property prediction as supervised data is often very limited. However, many important molecular properties depend on complex molecular characteristics -- such as the various 3D geometries a molecule may adopt or the types of chemical interactions it can form -- that are not explicitly encoded in the feature space and must be approximated from low amounts of data. Learning these characteristics can be difficult, especially for few-shot learning algorithms that are designed for fast adaptation to new tasks. In this work, we develop molecular embeddings that encode complex molecular characteristics to improve the performance of few-shot molecular property prediction. Our approach leverages large amounts of synthetic data, namely the results of molecular docking calculations, and a multi-task learning paradigm to structure the embedding space. On multiple molecular property prediction benchmarks, training from the embedding space substantially improves Multi-Task, MAML, and Prototypical Network few-shot learning performance. Our code is available at https://github.com/cfifty/IGNITE.

arXiv:2302.02025

Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks

Radio Access Networks (RANs) for telecommunications represent large agglomerations of interconnected hardware consisting of hundreds of thousands of transmitting devices (cells). Such networks undergo frequent and often heterogeneous changes caused by network operators, who are seeking to tune their system parameters for optimal performance. The effects of such changes are challenging to predict and will become even more so with the adoption of 5G/6G networks. Therefore, RAN monitoring is vital for network operators. We propose a self-supervised learning framework that leverages self-attention and self-distillation for this task. It works by detecting changes in Performance Measurement data, a collection of time-varying metrics which reflect a set of diverse measurements of the network performance at the cell level. Experimental results show that our approach outperforms the state of the art by 4% on a real-world based dataset consisting of about hundred thousands timeseries. It also has the merits of being scalable and generalizable. This allows it to provide deep insight into the specifics of mode of operation changes while relying minimally on expert knowledge.

arXiv:2302.02483

Multi-Task Self-Supervised Learning for Image Segmentation Task

Thanks to breakthroughs in AI and Deep learning methodology, Computer vision techniques are rapidly improving. Most computer vision applications require sophisticated image segmentation to comprehend what is image and to make an analysis of each section easier. Training deep learning networks for semantic segmentation required a large amount of annotated data, which presents a major challenge in practice as it is expensive and labor-intensive to produce such data. The paper presents 1. Self-supervised techniques to boost semantic segmentation performance using multi-task learning with Depth prediction and Surface Normalization . 2. Performance evaluation of the different types of weighing techniques (UW, Nash-MTL) used for Multi-task learning. NY2D dataset was used for performance evaluation. According to our evaluation, the Nash-MTL method outperforms single task learning(Semantic Segmentation).

arXiv:2302.02774

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instability in tuning optimizers and collapse of representations during training. Such challenges motivate the need for a theory to shed light on the complex interplay between the choice of data augmentation, network architecture, and training algorithm. We study such an interplay with a precise analysis of generalization performance on both pretraining and downstream tasks in a theory friendly setup, and highlight several insights for SSL practitioners that arise from our theory.

arXiv:2302.02249

Self-supervised Multi-view Disentanglement for Expansion of Visual Collections

Image search engines enable the retrieval of images relevant to a query image. In this work, we consider the setting where a query for similar images is derived from a collection of images. For visual search, the similarity measurements may be made along multiple axes, or views, such as style and color. We assume access to a set of feature extractors, each of which computes representations for a specific view. Our objective is to design a retrieval algorithm that effectively combines similarities computed over representations from multiple views. To this end, we propose a self-supervised learning method for extracting disentangled view-specific representations for images such that the inter-view overlap is minimized. We show how this allows us to compute the intent of a collection as a distribution over views. We show how effective retrieval can be performed by prioritizing candidate expansion images that match the intent of a query collection. Finally, we present a new querying mechanism for image search enabled by composing multiple collections and perform retrieval under this setting using the techniques presented in this paper.

arXiv:2302.02089

MOMA:Distill from Self-Supervised Teachers

Contrastive Learning and Masked Image Modelling have demonstrated exceptional performance on self-supervised representation learning, where Momentum Contrast (i.e., MoCo) and Masked AutoEncoder (i.e., MAE) are the state-of-the-art, respectively. In this work, we propose MOMA to distill from pre-trained MoCo and MAE in a self-supervised manner to collaborate the knowledge from both paradigms. We introduce three different mechanisms of knowledge transfer in the propsoed MOMA framework. : (1) Distill pre-trained MoCo to MAE. (2) Distill pre-trained MAE to MoCo (3) Distill pre-trained MoCo and MAE to a random initialized student. During the distillation, the teacher and the student are fed with original inputs and masked inputs, respectively. The learning is enabled by aligning the normalized representations from the teacher and the projected representations from the student. This simple design leads to efficient computation with extremely high mask ratio and dramatically reduced training epochs, and does not require extra considerations on the distillation target. The experiments show MOMA delivers compact student models with comparable performance to existing state-of-the-art methods, combining the power of both self-supervised learning paradigms. It presents competitive results against different benchmarks in computer vision. We hope our method provides an insight on transferring and adapting the knowledge from large-scale pre-trained models in a computationally efficient way.

arXiv:2302.01398

The unreasonable effectiveness of few-shot learning for machine translation

We demonstrate the potential of few-shot translation systems, trained with unpaired language data, for both high and low-resource language pairs. We show that with only 5 examples of high-quality translation data shown at inference, a transformer decoder-only model trained solely with self-supervised learning, is able to match specialized supervised state-of-the-art models as well as more general commercial translation systems. In particular, we outperform the best performing system on the WMT'21 English - Chinese news translation task by only using five examples of English - Chinese parallel data at inference. Moreover, our approach in building these models does not necessitate joint multilingual training or back-translation, is conceptually simple and shows the potential to extend to the multilingual setting. Furthermore, the resulting models are two orders of magnitude smaller than state-of-the-art language models. We then analyze the factors which impact the performance of few-shot translation systems, and highlight that the quality of the few-shot demonstrations heavily determines the quality of the translations generated by our models. Finally, we show that the few-shot paradigm also provides a way to control certain attributes of the translation -- we show that we are able to control for regional varieties and formality using only a five examples at inference, paving the way towards controllable machine translation systems.

arXiv:2302.01793

Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classification

Transferring the ImageNet pre-trained weights to the various remote sensing tasks has produced acceptable results and reduced the need for labeled samples. However, the domain differences between ground imageries and remote sensing images cause the performance of such transfer learning to be limited. Recent research has demonstrated that self-supervised learning methods capture visual features that are more discriminative and transferable than the supervised ImageNet weights. We are motivated by these facts to pre-train the in-domain representations of remote sensing imagery using contrastive self-supervised learning and transfer the learned features to other related remote sensing datasets. Specifically, we used the SimSiam algorithm to pre-train the in-domain knowledge of remote sensing datasets and then transferred the obtained weights to the other scene classification datasets. Thus, we have obtained state-of-the-art results on five land cover classification datasets with varying numbers of classes and spatial resolutions. In addition, By conducting appropriate experiments, including feature pre-training using datasets with different attributes, we have identified the most influential factors that make a dataset a good choice for obtaining in-domain features. We have transferred the features obtained by pre-training SimSiam on remote sensing datasets to various downstream tasks and used them as initial weights for fine-tuning. Moreover, we have linearly evaluated the obtained representations in cases where the number of samples per class is limited. Our experiments have demonstrated that using a higher-resolution dataset during the self-supervised pre-training stage results in learning more discriminative and general representations.

arXiv:2302.01409

Hyperbolic Contrastive Learning

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has shown competitive performance on several benchmark datasets. The embeddings of contrastive learning are arranged on a hypersphere that results in using the inner (dot) product as a distance measurement in Euclidean space. However, the underlying structure of many scientific fields like social networks, brain imaging, and computer graphics data exhibit highly non-Euclidean latent geometry. We propose a novel contrastive learning framework to learn semantic relationships in the hyperbolic space. Hyperbolic space is a continuous version of trees that naturally owns the ability to model hierarchical structures and is thus beneficial for efficient contrastive representation learning. We also extend the proposed Hyperbolic Contrastive Learning (HCL) to the supervised domain and studied the adversarial robustness of HCL. The comprehensive experiments show that our proposed method achieves better results on self-supervised pretraining, supervised classification, and higher robust accuracy than baseline methods.

arXiv:2302.01647공식 코드 · Papers with Code

Blockwise Self-Supervised Learning at Scale

Current state-of-the-art deep networks are all powered by backpropagation. In this paper, we explore alternatives to full backpropagation in the form of blockwise learning rules, leveraging the latest developments in self-supervised learning. We show that a blockwise pretraining procedure consisting of training independently the 4 main blocks of layers of a ResNet-50 with Barlow Twins' loss function at each block performs almost as well as end-to-end backpropagation on ImageNet: a linear probe trained on top of our blockwise pretrained model obtains a top-1 classification accuracy of 70.48%, only 1.1% below the accuracy of an end-to-end pretrained network (71.57% accuracy). We perform extensive experiments to understand the impact of different components within our method and explore a variety of adaptations of self-supervised learning to the blockwise paradigm, building an exhaustive understanding of the critical avenues for scaling local learning rules to large networks, with implications ranging from hardware design to neuroscience.

arXiv:2302.00988공식 코드 · Papers with Code

HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning

Recent advancements in 3D hand pose estimation have shown promising results, but its effectiveness has primarily relied on the availability of large-scale annotated datasets, the creation of which is a laborious and costly process. To alleviate the label-hungry limitation, we propose a self-supervised learning framework, HaMuCo, that learns a single-view hand pose estimator from multi-view pseudo 2D labels. However, one of the main challenges of self-supervised learning is the presence of noisy labels and the ``groupthink'' effect from multiple views. To overcome these issues, we introduce a cross-view interaction network that distills the single-view estimator by utilizing the cross-view correlated features and enforcing multi-view consistency to achieve collaborative learning. Both the single-view estimator and the cross-view interaction network are trained jointly in an end-to-end manner. Extensive experiments show that our method can achieve state-of-the-art performance on multi-view self-supervised hand pose estimation. Furthermore, the proposed cross-view interaction network can also be applied to hand pose estimation from multi-view input and outperforms previous methods under the same settings.

arXiv:2302.00722

A Survey of Deep Learning: From Activations to Transformers

Deep learning has made tremendous progress in the last decade. A key success factor is the large amount of architectures, layers, objectives, and optimization techniques. They include a myriad of variants related to attention, normalization, skip connections, transformers and self-supervised learning schemes -- to name a few. We provide a comprehensive overview of the most important, recent works in these areas to those who already have a basic understanding of deep learning. We hope that a holistic and unified treatment of influential, recent works helps researchers to form new connections between diverse areas of deep learning. We identify and discuss multiple patterns that summarize the key strategies for many of the successful innovations over the last decade as well as works that can be seen as rising stars. We also include a discussion on recent commercially built, closed-source models such as OpenAI's GPT-4 and Google's PaLM 2.

arXiv:2302.00207

Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach

With the rising demand for wireless services and increased awareness of the need for data protection, existing network traffic analysis and management architectures are facing unprecedented challenges in classifying and synthesizing the increasingly diverse services and applications. This paper proposes FS-GAN, a federated self-supervised learning framework to support automatic traffic analysis and synthesis over a large number of heterogeneous datasets. FS-GAN is composed of multiple distributed Generative Adversarial Networks (GANs), with a set of generators, each being designed to generate synthesized data samples following the distribution of an individual service traffic, and each discriminator being trained to differentiate the synthesized data samples and the real data samples of a local dataset. A federated learning-based framework is adopted to coordinate local model training processes of different GANs across different datasets. FS-GAN can classify data of unknown types of service and create synthetic samples that capture the traffic distribution of the unknown types. We prove that FS-GAN can minimize the Jensen-Shannon Divergence (JSD) between the distribution of real data across all the datasets and that of the synthesized data samples. FS-GAN also maximizes the JSD among the distributions of data samples created by different generators, resulting in each generator producing synthetic data samples that follow the same distribution as one particular service type. Extensive simulation results show that the classification accuracy of FS-GAN achieves over 20% improvement in average compared to the state-of-the-art clustering-based traffic analysis algorithms. FS-GAN also has the capability to synthesize highly complex mixtures of traffic types without requiring any human-labeled data samples.

arXiv:2302.00648

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms

This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised learning methods, DINO and data2vec, were evaluated and compared for their representation learning of vehicle images. The former contrasts local and global views while the latter uses masked prediction on multi-layered representations. In the latter case, supervised learning is employed to finetune a pretrained YOLOR object detector for detecting vehicle wheels, from which definitive wheel positional features are retrieved. The representations learned from these self-supervised learning methods were combined with the wheel positional features for the vehicle classification task. Particularly, a random wheel masking strategy was utilized to finetune the previously learned representations in harmony with the wheel positional features during the training of the classifier. Our experiments show that the data2vec-distilled representations, which are consistent with our wheel masking strategy, outperformed the DINO counterpart, resulting in a celebrated Top-1 classification accuracy of 97.2% for classifying the 13 vehicle classes defined by the Federal Highway Administration.

arXiv:2302.00353공식 코드 · Papers with Code

Towards Label-Efficient Incremental Learning: A Survey

The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many applications, non-incremental learning is unrealistic. To that end, researchers study incremental learning, where a learner is required to adapt to an incoming stream of data with a varying distribution while preventing forgetting of past knowledge. Significant progress has been made, however, the vast majority of works focus on the fully supervised setting, making these algorithms label-hungry thus limiting their real-life deployment. To that end, in this paper, we make the first attempt to survey recently growing interest in label-efficient incremental learning. We identify three subdivisions, namely semi-, few-shot- and self-supervised learning to reduce labeling efforts. Finally, we identify novel directions that can further enhance label-efficiency and improve incremental learning scalability. Project website: https://github.com/kilickaya/label-efficient-il.

arXiv:2301.12458

SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking

Generative graph self-supervised learning (SSL) aims to learn node representations by reconstructing the input graph data. However, most existing methods focus on unsupervised learning tasks only and very few work has shown its superiority over the state-of-the-art graph contrastive learning (GCL) models, especially on the classification task. While a very recent model has been proposed to bridge the gap, its performance on unsupervised learning tasks is still unknown. In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE). Specifically, SeeGera adopts the semi-implicit variational inference framework, a hierarchical variational framework, and mainly focuses on feature reconstruction and structure/feature masking. On the one hand, SeeGera co-embeds both nodes and features in the encoder and reconstructs both links and features in the decoder. Since feature embeddings contain rich semantic information on features, they can be combined with node embeddings to provide fine-grained knowledge for feature reconstruction. On the other hand, SeeGera adds an additional layer for structure/feature masking to the hierarchical variational framework, which boosts the model generalizability. We conduct extensive experiments comparing SeeGera with 9 other state-of-the-art competitors. Our results show that SeeGera can compare favorably against other state-of-the-art GCL methods in a variety of unsupervised and supervised learning tasks.

arXiv:2301.12189

Deciphering the Projection Head: Representation Evaluation Self-supervised Learning

Self-supervised learning (SSL) aims to learn intrinsic features without labels. Despite the diverse architectures of SSL methods, the projection head always plays an important role in improving the performance of the downstream task. In this work, we systematically investigate the role of the projection head in SSL. Specifically, the projection head targets the uniformity part of SSL, which pushes the dissimilar samples away from each other, thus enabling the encoder to focus on extracting semantic features. Based on this understanding, we propose a Representation Evaluation Design (RED) in SSL models in which a shortcut connection between the representation and the projection vectors is built. Extensive experiments with different architectures, including SimCLR, MoCo-V2, and SimSiam, on various datasets, demonstrate that the representation evaluation design can consistently improve the baseline models in the downstream tasks. The learned representation from the RED-SSL models shows superior robustness to unseen augmentations and out-of-distribution data.

arXiv:2301.12744

PointSmile: Point Self-supervised Learning via Curriculum Mutual Information

Self-supervised learning is attracting wide attention in point cloud processing. However, it is still not well-solved to gain discriminative and transferable features of point clouds for efficient training on downstream tasks, due to their natural sparsity and irregularity. We propose PointSmile, a reconstruction-free self-supervised learning paradigm by maximizing curriculum mutual information (CMI) across the replicas of point cloud objects. From the perspective of how-and-what-to-learn, PointSmile is designed to imitate human curriculum learning, i.e., starting with an easy curriculum and gradually increasing the difficulty of that curriculum. To solve "how-to-learn", we introduce curriculum data augmentation (CDA) of point clouds. CDA encourages PointSmile to learn from easy samples to hard ones, such that the latent space can be dynamically affected to create better embeddings. To solve "what-to-learn", we propose to maximize both feature- and class-wise CMI, for better extracting discriminative features of point clouds. Unlike most of existing methods, PointSmile does not require a pretext task, nor does it require cross-modal data to yield rich latent representations. We demonstrate the effectiveness and robustness of PointSmile in downstream tasks including object classification and segmentation. Extensive results show that our PointSmile outperforms existing self-supervised methods, and compares favorably with popular fully-supervised methods on various standard architectures.

arXiv:2301.12541

Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensing

In recent years Convolutional neural networks (CNN) have made significant progress in computer vision. These advancements have been applied to other areas, such as remote sensing and have shown satisfactory results. However, the lack of large labeled datasets and the inherent complexity of remote sensing problems have made it difficult to train deep CNNs for dense prediction problems. To solve this issue, ImageNet pretrained weights have been used as a starting point in various dense predictions tasks. Although this type of transfer learning has led to improvements, the domain difference between natural and remote sensing images has also limited the performance of deep CNNs. On the other hand, self-supervised learning methods for learning visual representations from large unlabeled images have grown substantially over the past two years. Accordingly, in this paper we have explored the effectiveness of in-domain representations in both supervised and self-supervised forms to solve the domain difference between remote sensing and the ImageNet dataset. The obtained weights from remote sensing images are utilized as initial weights for solving semantic segmentation and object detection tasks and state-of-the-art results are obtained. For self-supervised pre-training, we have utilized the SimSiam algorithm as it is simple and does not need huge computational resources. One of the most influential factors in acquiring general visual representations from remote sensing images is the pre-training dataset. To examine the effect of the pre-training dataset, equal-sized remote sensing datasets are used for pre-training. Our results have demonstrated that using datasets with a high spatial resolution for self-supervised representation learning leads to high performance in downstream tasks.

arXiv:2301.12025공식 코드 · Papers with Code

Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learning

Existing self-supervised techniques have extreme computational requirements and suffer a substantial drop in performance with a reduction in batch size or pretraining epochs. This paper presents Cross Architectural - Self Supervision (CASS), a novel self-supervised learning approach that leverages Transformer and CNN simultaneously. Compared to the existing state-of-the-art self-supervised learning approaches, we empirically show that CASS-trained CNNs and Transformers across four diverse datasets gained an average of 3.8% with 1% labeled data, 5.9% with 10% labeled data, and 10.13% with 100% labeled data while taking 69% less time. We also show that CASS is much more robust to changes in batch size and training epochs than existing state-of-the-art self-supervised learning approaches. We have open-sourced our code at https://github.com/pranavsinghps1/CASS.