PyTorchKR Papers

최신 논문

총 6,724편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2206.06461

Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC)

Self-supervised representation learning maps high-dimensional data into a meaningful embedding space, where samples of similar semantic contents are close to each other. Most of the recent representation learning methods maximize cosine similarity or minimize the distance between the embedding features of different views from the same sample usually on the $l2$ normalized unit hypersphere. To prevent the trivial solutions that all samples have the same embedding feature, various techniques have been developed, such as contrastive learning, stop gradient, variance and covariance regularization, etc. In this study, we propose MUlti-Segmental Informational Coding (MUSIC) for self-supervised representation learning. MUSIC divides the embedding feature into multiple segments that discriminatively partition samples into different semantic clusters and different segments focus on different partition principles. Information theory measurements are directly used to optimize MUSIC and theoretically guarantee trivial solutions are avoided. MUSIC does not depend on commonly used techniques, such as memory bank or large batches, asymmetry networks, gradient stopping, momentum weight updating, etc, making the training framework flexible. Our experiments demonstrate that MUSIC achieves better results than most related Barlow Twins and VICReg methods on ImageNet classification with linear probing, and requires neither deep projectors nor large feature dimensions. Code will be made available.

arXiv:2206.05836공식 코드 · Papers with Code

GLIPv2: Unifying Localization and Vision-Language Understanding

We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but also achieves mutual benefits between localization and understanding tasks. Experimental results show that a single GLIPv2 model (all model weights are shared) achieves near SoTA performance on various localization and understanding tasks. The model also shows (1) strong zero-shot and few-shot adaption performance on open-vocabulary object detection tasks and (2) superior grounding capability on VL understanding tasks. Code will be released at https://github.com/microsoft/GLIP.

arXiv:2206.06243공식 코드 · Papers with Code

Contrastive Learning for Unsupervised Domain Adaptation of Time Series

Unsupervised domain adaptation (UDA) aims at learning a machine learning model using a labeled source domain that performs well on a similar yet different, unlabeled target domain. UDA is important in many applications such as medicine, where it is used to adapt risk scores across different patient cohorts. In this paper, we develop a novel framework for UDA of time series data, called CLUDA. Specifically, we propose a contrastive learning framework to learn contextual representations in multivariate time series, so that these preserve label information for the prediction task. In our framework, we further capture the variation in the contextual representations between source and target domain via a custom nearest-neighbor contrastive learning. To the best of our knowledge, ours is the first framework to learn domain-invariant, contextual representation for UDA of time series data. We evaluate our framework using a wide range of time series datasets to demonstrate its effectiveness and show that it achieves state-of-the-art performance for time series UDA.

arXiv:2206.06177

Transductive CLIP with Class-Conditional Contrastive Learning

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains the label noise, which significantly degrades the discriminative power of the classification model. In this work, we propose Transductive CLIP, a novel framework for learning a classification network with noisy labels from scratch. Firstly, a class-conditional contrastive learning mechanism is proposed to mitigate the reliance on pseudo labels and boost the tolerance to noisy labels. Secondly, ensemble labels is adopted as a pseudo label updating strategy to stabilize the training of deep neural networks with noisy labels. This framework can reduce the impact of noisy labels from CLIP model effectively by combining both techniques. Experiments on multiple benchmark datasets demonstrate the substantial improvements over other state-of-the-art methods.

arXiv:2206.05225

ClamNet: Using contrastive learning with variable depth Unets for medical image segmentation

Unets have become the standard method for semantic segmentation of medical images, along with fully convolutional networks (FCN). Unet++ was introduced as a variant of Unet, in order to solve some of the problems facing Unet and FCNs. Unet++ provided networks with an ensemble of variable depth Unets, hence eliminating the need for professionals estimating the best suitable depth for a task. While Unet and all its variants, including Unet++ aimed at providing networks that were able to train well without requiring large quantities of annotated data, none of them attempted to eliminate the need for pixel-wise annotated data altogether. Obtaining such data for each disease to be diagnosed comes at a high cost. Hence such data is scarce. In this paper we use contrastive learning to train Unet++ for semantic segmentation of medical images using medical images from various sources including magnetic resonance imaging (MRI) and computed tomography (CT), without the need for pixel-wise annotations. Here we describe the architecture of the proposed model and the training method used. This is still a work in progress and so we abstain from including results in this paper. The results and the trained model would be made available upon publication or in subsequent versions of this paper on arxiv.

arXiv:2206.04739공식 코드 · Papers with Code

I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs

Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization. Recently, contrastive learning has emerged as a successful unsupervised representation learning method. Despite the prosperous development of contrastive learning in other domains, contrastive learning on hypergraphs remains little explored. In this paper, we propose TriCL (Tri-directional Contrastive Learning), a general framework for contrastive learning on hypergraphs. Its main idea is tri-directional contrast, and specifically, it aims to maximize in two augmented views the agreement (a) between the same node, (b) between the same group of nodes, and (c) between each group and its members. Together with simple but surprisingly effective data augmentation and negative sampling schemes, these three forms of contrast enable TriCL to capture both microscopic and mesoscopic structural information in node embeddings. Our extensive experiments using 13 baseline approaches, five datasets, and two tasks demonstrate the effectiveness of TriCL, and most noticeably, TriCL consistently outperforms not just unsupervised competitors but also (semi-)supervised competitors mostly by significant margins for node classification. The code and datasets are available at https://github.com/wooner49/TriCL.

arXiv:2206.04727

STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer

Modeling neural population dynamics underlying noisy single-trial spiking activities is essential for relating neural observation and behavior. A recent non-recurrent method - Neural Data Transformers (NDT) - has shown great success in capturing neural dynamics with low inference latency without an explicit dynamical model. However, NDT focuses on modeling the temporal evolution of the population activity while neglecting the rich covariation between individual neurons. In this paper we introduce SpatioTemporal Neural Data Transformer (STNDT), an NDT-based architecture that explicitly models responses of individual neurons in the population across time and space to uncover their underlying firing rates. In addition, we propose a contrastive learning loss that works in accordance with mask modeling objective to further improve the predictive performance. We show that our model achieves state-of-the-art performance on ensemble level in estimating neural activities across four neural datasets, demonstrating its capability to capture autonomous and non-autonomous dynamics spanning different cortical regions while being completely agnostic to the specific behaviors at hand. Furthermore, STNDT spatial attention mechanism reveals consistently important subsets of neurons that play a vital role in driving the response of the entire population, providing interpretability and key insights into how the population of neurons performs computation.

arXiv:2206.05259

Is Self-Supervised Learning More Robust Than Supervised Learning?

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has overlooked other behavioral aspects. In addition to accuracy, distributional robustness plays a critical role in the reliability of machine learning models. We design and conduct a series of robustness tests to quantify the behavioral differences between contrastive learning and supervised learning to downstream or pre-training data distribution changes. These tests leverage data corruptions at multiple levels, ranging from pixel-level gamma distortion to patch-level shuffling and to dataset-level distribution shift. Our tests unveil intriguing robustness behaviors of contrastive and supervised learning. On the one hand, under downstream corruptions, we generally observe that contrastive learning is surprisingly more robust than supervised learning. On the other hand, under pre-training corruptions, we find contrastive learning vulnerable to patch shuffling and pixel intensity change, yet less sensitive to dataset-level distribution change. We attempt to explain these results through the role of data augmentation and feature space properties. Our insight has implications in improving the downstream robustness of supervised learning.

arXiv:2206.04756공식 코드 · Papers with Code

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

Negative-free contrastive learning methods have attracted a lot of attention with simplicity and impressive performances for large-scale pretraining. However, its disentanglement property remains unexplored. In this paper, we examine negative-free contrastive learning methods to study the disentanglement property empirically. We find that existing disentanglement metrics fail to make meaningful measurements for high-dimensional representation models, so we propose a new disentanglement metric based on Mutual Information between latent representations and data factors. With this proposed metric, we benchmark the disentanglement property of negative-free contrastive learning on both popular synthetic datasets and a real-world dataset CelebA. Our study shows that the investigated methods can learn a well-disentangled subset of representation. As far as we know, we are the first to extend the study of disentangled representation learning to high-dimensional representation space and introduce negative-free contrastive learning methods into this area. The source code of this paper is available at \url{https://github.com/noahcao/disentanglement_lib_med}.

arXiv:2206.04726공식 코드 · Papers with Code

COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning

Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA on various downstream tasks. The graph augmentation step is a vital but scarcely studied step of GCL. In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks. Thus, instead of investigating graph augmentation in the input space, we alternatively propose to perform augmentations on the hidden features (feature augmentation). Inspired by so-called matrix sketching, we propose COSTA, a novel COvariance-preServing feaTure space Augmentation framework for GCL, which generates augmented features by maintaining a "good sketch" of original features. To highlight the superiority of feature augmentation with COSTA, we investigate a single-view setting (in addition to multi-view one) which conserves memory and computations. We show that the feature augmentation with COSTA achieves comparable/better results than graph augmentation based models.

arXiv:2206.04105

Words are all you need? Language as an approximation for human similarity judgments

Human similarity judgments are a powerful supervision signal for machine learning applications based on techniques such as contrastive learning, information retrieval, and model alignment, but classical methods for collecting human similarity judgments are too expensive to be used at scale. Recent methods propose using pre-trained deep neural networks (DNNs) to approximate human similarity, but pre-trained DNNs may not be available for certain domains (e.g., medical images, low-resource languages) and their performance in approximating human similarity has not been extensively tested. We conducted an evaluation of 611 pre-trained models across three domains -- images, audio, video -- and found that there is a large gap in performance between human similarity judgments and pre-trained DNNs. To address this gap, we propose a new class of similarity approximation methods based on language. To collect the language data required by these new methods, we also developed and validated a novel adaptive tag collection pipeline. We find that our proposed language-based methods are significantly cheaper, in the number of human judgments, than classical methods, but still improve performance over the DNN-based methods. Finally, we also develop `stacked' methods that combine language embeddings with DNN embeddings, and find that these consistently provide the best approximations for human similarity across all three of our modalities. Based on the results of this comprehensive study, we provide a concise guide for researchers interested in collecting or approximating human similarity data. To accompany this guide, we also release all of the similarity and language data, a total of 206,339 human judgments, that we collected in our experiments, along with a detailed breakdown of all modeling results.

arXiv:2206.04028공식 코드 · Papers with Code

CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving

Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and capture partial views for the contrastive objective. This is infeasible in outdoor scenes with moving objects, obstacles, and sensors. In this paper, we propose CO^3, namely Cooperative Contrastive Learning and Contextual Shape Prediction, to learn 3D representation for outdoor-scene point clouds in an unsupervised manner. CO^3 has several merits compared to existing methods. (1) It utilizes LiDAR point clouds from vehicle-side and infrastructure-side to build views that differ enough but meanwhile maintain common semantic information for contrastive learning, which are more appropriate than views built by previous methods. (2) Alongside the contrastive objective, shape context prediction is proposed as pre-training goal and brings more task-relevant information for unsupervised 3D point cloud representation learning, which are beneficial when transferring the learned representation to downstream detection tasks. (3) As compared to previous methods, representation learned by CO^3 is able to be transferred to different outdoor scene dataset collected by different type of LiDAR sensors. (4) CO^3 improves current state-of-the-art methods on both Once and KITTI datasets by up to 2.58 mAP. Codes and models will be released. We believe CO^3 will facilitate understanding LiDAR point clouds in outdoor scene.

arXiv:2206.03888

ConFUDA: Contrastive Fewshot Unsupervised Domain Adaptation for Medical Image Segmentation

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain. Contrastive learning (CL) in the context of UDA can help to better separate classes in feature space. However, in image segmentation, the large memory footprint due to the computation of the pixel-wise contrastive loss makes it prohibitive to use. Furthermore, labeled target data is not easily available in medical imaging, and obtaining new samples is not economical. As a result, in this work, we tackle a more challenging UDA task when there are only a few (fewshot) or a single (oneshot) image available from the target domain. We apply a style transfer module to mitigate the scarcity of target samples. Then, to align the source and target features and tackle the memory issue of the traditional contrastive loss, we propose the centroid-based contrastive learning (CCL) and a centroid norm regularizer (CNR) to optimize the contrastive pairs in both direction and magnitude. In addition, we propose multi-partition centroid contrastive learning (MPCCL) to further reduce the variance in the target features. Fewshot evaluation on MS-CMRSeg dataset demonstrates that ConFUDA improves the segmentation performance by 0.34 of the Dice score on the target domain compared with the baseline, and 0.31 Dice score improvement in a more rigorous oneshot setting.

arXiv:2206.02796

Mixed Graph Contrastive Network for Semi-Supervised Node Classification

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance of the GNNs in this field. To alleviate the collapse of node representations in semi-supervised scenario, we propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN). In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries and improving the cross-view consistency of the latent representation. Specifically, we first adopt an interpolation-based strategy to conduct data augmentation in the latent space and then force the prediction model to change linearly between samples. Second, we enable the learned network to tell apart samples across two interpolation-perturbed views through forcing the correlation matrix across views to approximate an identity matrix. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discriminative representation learning. Extensive experimental results on six datasets demonstrate the effectiveness and the generality of MGCN compared to the existing state-of-the-art methods.

arXiv:2206.02457공식 코드 · Papers with Code

Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised counterparts. We attribute this to the quality of positive and negative samples, and aim to improve both. Specifically, for positive samples, we propose switch-case augmentation to flip the case of the first letter of randomly selected words in a sentence. This is to counteract the intrinsic bias of pre-trained token embeddings to frequency, word cases and subwords. For negative samples, we sample hard negatives from the whole dataset based on a pre-trained language model. Combining the above two methods with SimCSE, our proposed Contrastive learning with Augmented and Retrieved Data for Sentence embedding (CARDS) method significantly surpasses the current SOTA on STS benchmarks in the unsupervised setting.

arXiv:2206.01816공식 코드 · Papers with Code

From $t$-SNE to UMAP with contrastive learning

Neighbor embedding methods $t$-SNE and UMAP are the de facto standard for visualizing high-dimensional datasets. Motivated from entirely different viewpoints, their loss functions appear to be unrelated. In practice, they yield strongly differing embeddings and can suggest conflicting interpretations of the same data. The fundamental reasons for this and, more generally, the exact relationship between $t$-SNE and UMAP have remained unclear. In this work, we uncover their conceptual connection via a new insight into contrastive learning methods. Noise-contrastive estimation can be used to optimize $t$-SNE, while UMAP relies on negative sampling, another contrastive method. We find the precise relationship between these two contrastive methods and provide a mathematical characterization of the distortion introduced by negative sampling. Visually, this distortion results in UMAP generating more compact embeddings with tighter clusters compared to $t$-SNE. We exploit this new conceptual connection to propose and implement a generalization of negative sampling, allowing us to interpolate between (and even extrapolate beyond) $t$-SNE and UMAP and their respective embeddings. Moving along this spectrum of embeddings leads to a trade-off between discrete / local and continuous / global structures, mitigating the risk of over-interpreting ostensible features of any single embedding. We provide a PyTorch implementation.

arXiv:2206.02770

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

Large sparsely-activated models have obtained excellent performance in multiple domains. However, such models are typically trained on a single modality at a time. We present the Language-Image MoE, LIMoE, a sparse mixture of experts model capable of multimodal learning. LIMoE accepts both images and text simultaneously, while being trained using a contrastive loss. MoEs are a natural fit for a multimodal backbone, since expert layers can learn an appropriate partitioning of modalities. However, new challenges arise; in particular, training stability and balanced expert utilization, for which we propose an entropy-based regularization scheme. Across multiple scales, we demonstrate remarkable performance improvement over dense models of equivalent computational cost. LIMoE-L/16 trained comparably to CLIP-L/14 achieves 78.6% zero-shot ImageNet accuracy (vs. 76.2%), and when further scaled to H/14 (with additional data) it achieves 84.1%, comparable to state-of-the-art methods which use larger custom per-modality backbones and pre-training schemes. We analyse the quantitative and qualitative behavior of LIMoE, and demonstrate phenomena such as differing treatment of the modalities and the organic emergence of modality-specific experts.

arXiv:2206.02343

Contrastive Graph Multimodal Model for Text Classification in Videos

The extraction of text information in videos serves as a critical step towards semantic understanding of videos. It usually involved in two steps: (1) text recognition and (2) text classification. To localize texts in videos, we can resort to large numbers of text recognition methods based on OCR technology. However, to our knowledge, there is no existing work focused on the second step of video text classification, which will limit the guidance to downstream tasks such as video indexing and browsing. In this paper, we are the first to address this new task of video text classification by fusing multimodal information to deal with the challenging scenario where different types of video texts may be confused with various colors, unknown fonts and complex layouts. In addition, we tailor a specific module called CorrelationNet to reinforce feature representation by explicitly extracting layout information. Furthermore, contrastive learning is utilized to explore inherent connections between samples using plentiful unlabeled videos. Finally, we construct a new well-defined industrial dataset from the news domain, called TI-News, which is dedicated to building and evaluating video text recognition and classification applications. Extensive experiments on TI-News demonstrate the effectiveness of our method.

arXiv:2206.02180

Semi-Supervised Learning for Mars Imagery Classification and Segmentation

With the progress of Mars exploration, numerous Mars image data are collected and need to be analyzed. However, due to the imbalance and distortion of Martian data, the performance of existing computer vision models is unsatisfactory. In this paper, we introduce a semi-supervised framework for machine vision on Mars and try to resolve two specific tasks: classification and segmentation. Contrastive learning is a powerful representation learning technique. However, there is too much information overlap between Martian data samples, leading to a contradiction between contrastive learning and Martian data. Our key idea is to reconcile this contradiction with the help of annotations and further take advantage of unlabeled data to improve performance. For classification, we propose to ignore inner-class pairs on labeled data as well as neglect negative pairs on unlabeled data, forming supervised inter-class contrastive learning and unsupervised similarity learning. For segmentation, we extend supervised inter-class contrastive learning into an element-wise mode and use online pseudo labels for supervision on unlabeled areas. Experimental results show that our learning strategies can improve the classification and segmentation models by a large margin and outperform state-of-the-art approaches.

arXiv:2206.02531

3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation

Image-based object pose estimation sounds amazing because in real applications the shape of object is oftentimes not available or not easy to take like photos. Although it is an advantage to some extent, un-explored shape information in 3D vision learning problem looks like "flaws in jade". In this paper, we deal with the problem in a reasonable new setting, namely 3D shape is exploited in the training process, and the testing is still purely image-based. We enhance the performance of image-based methods for category-agnostic object pose estimation by exploiting 3D knowledge learned by a multi-modal method. Specifically, we propose a novel contrastive knowledge distillation framework that effectively transfers 3D-augmented image representation from a multi-modal model to an image-based model. We integrate contrastive learning into the two-stage training procedure of knowledge distillation, which formulates an advanced solution to combine these two approaches for cross-modal tasks. We experimentally report state-of-the-art results compared with existing category-agnostic image-based methods by a large margin (up to +5% improvement on ObjectNet3D dataset), demonstrating the effectiveness of our method.