PyTorchKR Papers

최신 논문

총 6,725편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2306.08541

Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval

Recently, encoders like ViT (vision transformer) and ResNet have been trained on vast datasets and utilized as perceptual metrics for comparing sketches and images, as well as multi-domain encoders in a zero-shot setting. However, there has been limited effort to quantify the granularity of these encoders. Our work addresses this gap by focusing on multi-modal 2D projections of individual 3D instances. This task holds crucial implications for retrieval and sketch-based modeling. We show that in a zero-shot setting, the more abstract the sketch, the higher the likelihood of incorrect image matches. Even within the same sketch domain, sketches of the same object drawn in different styles, for example by distinct individuals, might not be accurately matched. One of the key findings of our research is that meticulous fine-tuning on one class of 3D shapes can lead to improved performance on other shape classes, reaching or surpassing the accuracy of supervised methods. We compare and discuss several fine-tuning strategies. Additionally, we delve deeply into how the scale of an object in a sketch influences the similarity of features at different network layers, helping us identify which network layers provide the most accurate matching. Significantly, we discover that ViT and ResNet perform best when dealing with similar object scales. We believe that our work will have a significant impact on research in the sketch domain, providing insights and guidance on how to adopt large pretrained models as perceptual losses.

arXiv:2306.08194

Learning on Graphs under Label Noise

Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current techniques often presume that label information of nodes is accurate, which may not be the case in real-world applications. To tackle this issue, we investigate the problem of learning on graphs with label noise and develop a novel approach dubbed Consistent Graph Neural Network (CGNN) to solve it. Specifically, we employ graph contrastive learning as a regularization term, which promotes two views of augmented nodes to have consistent representations. Since this regularization term cannot utilize label information, it can enhance the robustness of node representations to label noise. Moreover, to detect noisy labels on the graph, we present a sample selection technique based on the homophily assumption, which identifies noisy nodes by measuring the consistency between the labels with their neighbors. Finally, we purify these confident noisy labels to permit efficient semantic graph learning. Extensive experiments on three well-known benchmark datasets demonstrate the superiority of our CGNN over competing approaches.

arXiv:2306.07848

GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition

Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of gender-attribute-enhanced contrastive language-audio pretraining (CLAP) method for SER. Specifically, we first construct an effective emotion CLAP (Emo-CLAP) for SER, using pre-trained text and audio encoders. Second, given the significance of gender information in SER, two novel multi-task learning based GEmo-CLAP (ML-GEmo-CLAP) and soft label based GEmo-CLAP (SL-GEmo-CLAP) models are further proposed to incorporate gender information of speech signals, forming more reasonable objectives. Experiments on IEMOCAP indicate that our proposed two GEmo-CLAPs consistently outperform Emo-CLAP with different pre-trained models. Remarkably, the proposed WavLM-based SL-GEmo-CLAP obtains the best WAR of 83.16\%, which performs better than state-of-the-art SER methods.

arXiv:2306.07744공식 코드 · Papers with Code

Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classification (CTC) loss. However, both approaches suffer from specific weaknesses: toolkits are known for their complexity, and CTC systems use a loss designed for transcription which can limit alignment accuracy. In this paper, we use instead a contrastive learning procedure that derives cross-modal embeddings linking the audio and text domains. This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment. The system is not only the first to yield an average absolute error below 0.2 seconds on the standard Jamendo dataset but it is also robust to other languages, even when trained on English data only. Finally, we release word-level alignments for the JamendoLyrics Multi-Lang dataset.

arXiv:2306.07646

Enhanced Multimodal Representation Learning with Cross-modal KD

This paper explores the tasks of leveraging auxiliary modalities which are only available at training to enhance multimodal representation learning through cross-modal Knowledge Distillation (KD). The widely adopted mutual information maximization-based objective leads to a short-cut solution of the weak teacher, i.e., achieving the maximum mutual information by simply making the teacher model as weak as the student model. To prevent such a weak solution, we introduce an additional objective term, i.e., the mutual information between the teacher and the auxiliary modality model. Besides, to narrow down the information gap between the student and teacher, we further propose to minimize the conditional entropy of the teacher given the student. Novel training schemes based on contrastive learning and adversarial learning are designed to optimize the mutual information and the conditional entropy, respectively. Experimental results on three popular multimodal benchmark datasets have shown that the proposed method outperforms a range of state-of-the-art approaches for video recognition, video retrieval and emotion classification.

arXiv:2306.07699공식 코드 · Papers with Code

Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs

Temporal Graph Learning, which aims to model the time-evolving nature of graphs, has gained increasing attention and achieved remarkable performance recently. However, in reality, graph structures are often incomplete and noisy, which hinders temporal graph networks (TGNs) from learning informative representations. Graph contrastive learning uses data augmentation to generate plausible variations of existing data and learn robust representations. However, rule-based augmentation approaches may be suboptimal as they lack learnability and fail to leverage rich information from downstream tasks. To address these issues, we propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs, which learns better graph structures for downstream tasks through adding potential temporal edges. In particular, it predicts time-aware context embedding based on previously observed interactions and uses the Gumble-Top-K to select the closest candidate edges to this context embedding. Additionally, several candidate sampling strategies are proposed to ensure both efficiency and diversity. Furthermore, we jointly learn the graph structure and TGNs in an end-to-end manner and perform inference on the refined graph. Extensive experiments on temporal link prediction benchmarks demonstrate that TGSL yields significant gains for the popular TGNs such as TGAT and GraphMixer, and it outperforms other contrastive learning methods on temporal graphs. We release the code at https://github.com/ViktorAxelsen/TGSL.

arXiv:2306.06276공식 코드 · Papers with Code

Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression Values

Recent advancements in image classification have demonstrated that contrastive learning (CL) can aid in further learning tasks by acquiring good feature representation from a limited number of data samples. In this paper, we applied CL to tumor transcriptomes and clinical data to learn feature representations in a low-dimensional space. We then utilized these learned features to train a classifier to categorize tumors into a high- or low-risk group of recurrence. Using data from The Cancer Genome Atlas (TCGA), we demonstrated that CL can significantly improve classification accuracy. Specifically, our CL-based classifiers achieved an area under the receiver operating characteristic curve (AUC) greater than 0.8 for 14 types of cancer, and an AUC greater than 0.9 for 2 types of cancer. We also developed CL-based Cox (CLCox) models for predicting cancer prognosis. Our CLCox models trained with the TCGA data outperformed existing methods significantly in predicting the prognosis of 19 types of cancer under consideration. The performance of CLCox models and CL-based classifiers trained with TCGA lung and prostate cancer data were validated using the data from two independent cohorts. We also show that the CLCox model trained with the whole transcriptome significantly outperforms the Cox model trained with the 21 genes of Oncotype DX that is in clinical use for breast cancer patients. CL-based classifiers and CLCox models for 19 types of cancer are publicly available and can be used to predict cancer prognosis using the RNA-seq transcriptome of an individual tumor. Python codes for model training and testing are also publicly accessible, and can be applied to train new CL-based models using gene expression data of tumors.

arXiv:2306.06936

CARL-G: Clustering-Accelerated Representation Learning on Graphs

Self-supervised learning on graphs has made large strides in achieving great performance in various downstream tasks. However, many state-of-the-art methods suffer from a number of impediments, which prevent them from realizing their full potential. For instance, contrastive methods typically require negative sampling, which is often computationally costly. While non-contrastive methods avoid this expensive step, most existing methods either rely on overly complex architectures or dataset-specific augmentations. In this paper, we ask: Can we borrow from classical unsupervised machine learning literature in order to overcome those obstacles? Guided by our key insight that the goal of distance-based clustering closely resembles that of contrastive learning: both attempt to pull representations of similar items together and dissimilar items apart. As a result, we propose CARL-G - a novel clustering-based framework for graph representation learning that uses a loss inspired by Cluster Validation Indices (CVIs), i.e., internal measures of cluster quality (no ground truth required). CARL-G is adaptable to different clustering methods and CVIs, and we show that with the right choice of clustering method and CVI, CARL-G outperforms node classification baselines on 4/5 datasets with up to a 79x training speedup compared to the best-performing baseline. CARL-G also performs at par or better than baselines in node clustering and similarity search tasks, training up to 1,500x faster than the best-performing baseline. Finally, we also provide theoretical foundations for the use of CVI-inspired losses in graph representation learning.

arXiv:2306.06579공식 코드 · Papers with Code

Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder

In this work, we investigate the time series representation learning problem using self-supervised techniques. Contrastive learning is well-known in this area as it is a powerful method for extracting information from the series and generating task-appropriate representations. Despite its proficiency in capturing time series characteristics, these techniques often overlook a critical factor - the inherent noise in this type of data, a consideration usually emphasized in general time series analysis. Moreover, there is a notable absence of attention to developing efficient yet lightweight encoder architectures, with an undue focus on delivering contrastive losses. Our work address these gaps by proposing an innovative training strategy that promotes consistent representation learning, accounting for the presence of noise-prone signals in natural time series. Furthermore, we propose an encoder architecture that incorporates dilated convolution within the Inception block, resulting in a scalable and robust network with a wide receptive field. Experimental findings underscore the effectiveness of our method, consistently outperforming state-of-the-art approaches across various tasks, including forecasting, classification, and abnormality detection. Notably, our method attains the top rank in over two-thirds of the classification UCR datasets, utilizing only 40% of the parameters compared to the second-best approach. Our source code for CoInception framework is accessible at https://github.com/anhduy0911/CoInception.

arXiv:2306.06306공식 코드 · Papers with Code

DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents

Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding single image associated with a single piece of text, they often ignore the alignment at the intra-document level, consisting of multiple sentences with multiple images. In this work, we propose DocumentCLIP, a salience-aware contrastive learning framework to enforce vision-language pretraining models to comprehend the interaction between images and longer text within documents. Our model is beneficial for the real-world multimodal document understanding like news article, magazines, product descriptions, which contain linguistically and visually richer content. To the best of our knowledge, we are the first to explore multimodal intra-document links by contrastive learning. In addition, we collect a large Wikipedia dataset for pretraining, which provides various topics and structures. Experiments show DocumentCLIP not only outperforms the state-of-the-art baselines in the supervised setting, but also achieves the best zero-shot performance in the wild after human evaluation. Our code is available at https://github.com/FuxiaoLiu/DocumentCLIP.

arXiv:2306.06066공식 코드 · Papers with Code

Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing Image Scenes

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene classification, the cross-modal feature alignment methods have been proposed in recent years. These methods mainly focus on matching the visual features of each image scene with their corresponding semantic descriptors in the latent space. Less attention has been paid to the contrastive relationships between different image scenes and different semantic descriptors. In light of the challenge of large intra-class difference and inter-class similarity among image scenes and the potential noisy samples, these methods are susceptible to the influence of the instances which are far from these of the same classes and close to these of other classes. In this work, we propose a multi-level cross-modal feature alignment method via contrastive learning for zero-shot classification of remote sensing image scenes. While promoting the single-instance level positive alignment between each image scene with their corresponding semantic descriptors, the proposed method takes the cross-instance contrastive relationships into consideration,and learns to keep the visual and semantic features of different classes in the latent space apart from each other. Extensive experiments have been done to evaluate the performance of the proposed method. The results show that our proposed method outperforms state of the art methods for zero-shot remote sensing image scene classification. All the code and data are available at github https://github.com/masuqiang/MCFA-Pytorch

arXiv:2306.05987

Liquidity takers behavior representation through a contrastive learning approach

Thanks to the access to the labeled orders on the CAC40 data from Euronext, we are able to analyze agents' behaviors in the market based on their placed orders. In this study, we construct a self-supervised learning model using triplet loss to effectively learn the representation of agent market orders. By acquiring this learned representation, various downstream tasks become feasible. In this work, we utilize the K-means clustering algorithm on the learned representation vectors of agent orders to identify distinct behavior types within each cluster.

arXiv:2306.05528

A brief review of contrastive learning applied to astrophysics

Reliable tools to extract patterns from high-dimensionality spaces are becoming more necessary as astronomical datasets increase both in volume and complexity. Contrastive Learning is a self-supervised machine learning algorithm that extracts informative measurements from multi-dimensional datasets, which has become increasingly popular in the computer vision and Machine Learning communities in recent years. To do so, it maximizes the agreement between the information extracted from augmented versions of the same input data, making the final representation invariant to the applied transformations. Contrastive Learning is particularly useful in astronomy for removing known instrumental effects and for performing supervised classifications and regressions with a limited amount of available labels, showing a promising avenue towards \emph{Foundation Models}. This short review paper briefly summarizes the main concepts behind contrastive learning and reviews the first promising applications to astronomy. We include some practical recommendations on which applications are particularly attractive for contrastive learning.

arXiv:2306.05439

Contrastive Representation Disentanglement for Clustering

Clustering continues to be a significant and challenging task. Recent studies have demonstrated impressive results by applying clustering to feature representations acquired through self-supervised learning, particularly on small datasets. However, when dealing with datasets containing a large number of clusters, such as ImageNet, current methods struggle to achieve satisfactory clustering performance. In this paper, we introduce a novel method called Contrastive representation Disentanglement for Clustering (CDC) that leverages contrastive learning to directly disentangle the feature representation for clustering. In CDC, we decompose the representation into two distinct components: one component encodes categorical information under an equipartition constraint, and the other component captures instance-specific factors. To train our model, we propose a contrastive loss that effectively utilizes both components of the representation. We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation. Further analysis of the gradients reveals that larger weights emphasize a stronger focus on hard negative samples. As a result, the proposed loss exhibits strong expressiveness, enabling efficient disentanglement of categorical information. Through experimental evaluation on various benchmark datasets, our method demonstrates either state-of-the-art or highly competitive clustering performance. Notably, on the complete ImageNet dataset, we achieve an accuracy of 53.4%, surpassing existing methods by a substantial margin of +10.2%.

arXiv:2306.04641공식 코드 · Papers with Code

Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning

Human activity recognition (HAR) is a time series classification task that focuses on identifying the motion patterns from human sensor readings. Adequate data is essential but a major bottleneck for training a generalizable HAR model, which assists customization and optimization of online web applications. However, it is costly in time and economy to collect large-scale labeled data in reality, i.e., the low-resource challenge. Meanwhile, data collected from different persons have distribution shifts due to different living habits, body shapes, age groups, etc. The low-resource and distribution shift challenges are detrimental to HAR when applying the trained model to new unseen subjects. In this paper, we propose a novel approach called Diverse and Discriminative representation Learning (DDLearn) for generalizable low-resource HAR. DDLearn simultaneously considers diversity and discrimination learning. With the constructed self-supervised learning task, DDLearn enlarges the data diversity and explores the latent activity properties. Then, we propose a diversity preservation module to preserve the diversity of learned features by enlarging the distribution divergence between the original and augmented domains. Meanwhile, DDLearn also enhances semantic discrimination by learning discriminative representations with supervised contrastive learning. Extensive experiments on three public HAR datasets demonstrate that our method significantly outperforms state-of-art methods by an average accuracy improvement of 9.5% under the low-resource distribution shift scenarios, while being a generic, explainable, and flexible framework. Code is available at: https://github.com/microsoft/robustlearn.

arXiv:2306.05101공식 코드 · Papers with Code

Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning

We introduce a novel Pseudo-Negative Regularization (PNR) framework for effective continual self-supervised learning (CSSL). Our PNR leverages pseudo-negatives obtained through model-based augmentation in a way that newly learned representations may not contradict what has been learned in the past. Specifically, for the InfoNCE-based contrastive learning methods, we define symmetric pseudo-negatives obtained from current and previous models and use them in both main and regularization loss terms. Furthermore, we extend this idea to non-contrastive learning methods which do not inherently rely on negatives. For these methods, a pseudo-negative is defined as the output from the previous model for a differently augmented version of the anchor sample and is asymmetrically applied to the regularization term. Extensive experimental results demonstrate that our PNR framework achieves state-of-the-art performance in representation learning during CSSL by effectively balancing the trade-off between plasticity and stability.

arXiv:2306.05011

Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce

Ranking model plays an essential role in e-commerce search and recommendation. An effective ranking model should give a personalized ranking list for each user according to the user preference. Existing algorithms usually extract a user representation vector from the user behavior sequence, then feed the vector into a feed-forward network (FFN) together with other features for feature interactions, and finally produce a personalized ranking score. Despite tremendous progress in the past, there is still room for improvement. Firstly, the personalized patterns of feature interactions for different users are not explicitly modeled. Secondly, most of existing algorithms have poor personalized ranking results for long-tail users with few historical behaviors due to the data sparsity. To overcome the two challenges, we propose Attention Weighted Mixture of Experts (AW-MoE) with contrastive learning for personalized ranking. Firstly, AW-MoE leverages the MoE framework to capture personalized feature interactions for different users. To model the user preference, the user behavior sequence is simultaneously fed into expert networks and the gate network. Within the gate network, one gate unit and one activation unit are designed to adaptively learn the fine-grained activation vector for experts using an attention mechanism. Secondly, a random masking strategy is applied to the user behavior sequence to simulate long-tail users, and an auxiliary contrastive loss is imposed to the output of the gate network to improve the model generalization for these users. This is validated by a higher performance gain on the long-tail user test set. Experiment results on a JD real production dataset and a public dataset demonstrate the effectiveness of AW-MoE, which significantly outperforms state-of-art methods. Notably, AW-MoE has been successfully deployed in the JD e-commerce search engine, ...

arXiv:2306.04739공식 코드 · Papers with Code

Automatic retrieval of corresponding US views in longitudinal examinations

Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual measurements are subject to large variability, particularly since the scans are typically acquired on different days and potentially by different operators. In this paper, we propose a self-supervised contrastive learning approach to automatically retrieve similar ultrasound muscle views at different scan times. Three different models were compared using data from 67 patients acquired in the ICU. Results indicate that our contrastive model outperformed a supervised baseline model in the task of view retrieval with an AUC of 73.52% and when combined with an automatic segmentation model achieved 5.7%+/-0.24% error in cross-sectional area. Furthermore, a user study survey confirmed the efficacy of our model for muscle view retrieval.

arXiv:2306.05411공식 코드 · Papers with Code

R-MAE: Regions Meet Masked Autoencoders

In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to learn from groups of pixels or regions. Specifically, we design an architecture which efficiently addresses the one-to-many mapping between images and regions, while being highly effective especially with high-quality regions. When integrated with MAE, our approach (R-MAE) demonstrates consistent improvements across various pre-training datasets and downstream detection and segmentation benchmarks, with negligible computational overheads. Beyond the quantitative evaluation, our analysis indicates the models pre-trained with masked region autoencoding unlock the potential for interactive segmentation. The code is provided at https://github.com/facebookresearch/r-mae.

arXiv:2306.05145

Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image

Reconstructing category-specific objects from a single image is a challenging task that requires inferring the geometry and appearance of an object from a limited viewpoint. Existing methods typically rely on local feature retrieval based on re-projection with known camera intrinsic, which are slow and prone to distortion at viewpoints distant from the input image. In this paper, we present Variable Radiance Field (VRF), a novel framework that can efficiently reconstruct category-specific objects from a single image without known camera parameters. Our key contributions are: (1) We parameterize the geometry and appearance of the object using a multi-scale global feature extractor, which avoids frequent point-wise feature retrieval and camera dependency. We also propose a contrastive learning-based pretraining strategy to improve the feature extractor. (2) We reduce the geometric complexity of the object by learning a category template, and use hypernetworks to generate a small neural radiance field for fast and instance-specific rendering. (3) We align each training instance to the template space using a learned similarity transformation, which enables semantic-consistent learning across different objects. We evaluate our method on the CO3D dataset and show that it outperforms existing methods in terms of quality and speed. We also demonstrate its applicability to shape interpolation and object placement tasks.