The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the combination of global and local feature information. This paper proposes a multi-network contrastive learning framework based on global and local representations. We introduce global and local feature information for self-supervised contrastive learning through multiple networks. The model learns feature information at different scales of an image by contrasting the embedding pairs generated by multiple networks. The framework also expands the number of samples used for contrast and improves the training efficiency of the model. Linear evaluation results on three benchmark datasets show that our method outperforms several existing classical self-supervised learning methods.
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance with a price of introducing imbalance between instances of head class and tail class, which may ignore the underlying rich semantic substructures of the former and exaggerate the biases in the latter. We overcome these drawbacks by a novel ``subclass-balancing contrastive learning (SBCL)'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes and enforce representations to capture the two-layer class hierarchy between the original classes and their subclasses. Since the clustering is conducted in the representation space and updated during the course of training, the subclass labels preserve the semantic substructures of head classes. Meanwhile, it does not overemphasize tail class samples, so each individual instance contribute to the representation learning equally. Hence, our method achieves both the instance- and subclass-balance, while the original class labels are also learned through contrastive learning among subclasses from different classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance. In addition, we present extensive analyses and ablation studies of SBCL to verify its advantages.
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised pre-training excel at capturing longer-range global patterns and enabling better feature discrimination, while MIM can introduce more local and diverse attention across all transformer layers. In this paper, we explore how to obtain a model that combines their strengths. We start by examining previous feature distillation and mask feature reconstruction methods and identify their limitations. We find that their increasing diversity mainly derives from the asymmetric designs, but these designs may in turn compromise the discrimination ability. In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model. Hybrid Distill imitates the token relations of the MIM teacher to alleviate attention collapse, as well as distills the feature maps of the supervised/CL teacher to enable discrimination. Furthermore, a progressive redundant token masking strategy is also utilized to reduce the distilling costs and avoid falling into local optima. Experiment results prove that Hybrid Distill can achieve superior performance on different benchmarks.
Self-supervised contrastive learning (SSCL) has achieved significant milestones in remote sensing image (RSI) understanding. Its essence lies in designing an unsupervised instance discrimination pretext task to extract image features from a large number of unlabeled images that are beneficial for downstream tasks. However, existing instance discrimination based SSCL suffer from two limitations when applied to the RSI semantic segmentation task: 1) Positive sample confounding issue; 2) Feature adaptation bias. It introduces a feature adaptation bias when applied to semantic segmentation tasks that require pixel-level or object-level features. In this study, We observed that the discrimination information can be mapped to specific regions in RSI through the gradient of unsupervised contrastive loss, these specific regions tend to contain singular ground objects. Based on this, we propose contrastive learning with Gradient guided Sampling Strategy (GraSS) for RSI semantic segmentation. GraSS consists of two stages: Instance Discrimination warm-up (ID warm-up) and Gradient guided Sampling contrastive training (GS training). The ID warm-up aims to provide initial discrimination information to the contrastive loss gradients. The GS training stage aims to utilize the discrimination information contained in the contrastive loss gradients and adaptively select regions in RSI patches that contain more singular ground objects, in order to construct new positive and negative samples. Experimental results on three open datasets demonstrate that GraSS effectively enhances the performance of SSCL in high-resolution RSI semantic segmentation. Compared to seven baseline methods from five different types of SSCL, GraSS achieves an average improvement of 1.57\% and a maximum improvement of 3.58\% in terms of mean intersection over the union. The source code is available at https://github.com/GeoX-Lab/GraSS
Multimodal Sentiment Analysis leverages multimodal signals to detect the sentiment of a speaker. Previous approaches concentrate on performing multimodal fusion and representation learning based on general knowledge obtained from pretrained models, which neglects the effect of domain-specific knowledge. In this paper, we propose Contrastive Knowledge Injection (ConKI) for multimodal sentiment analysis, where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture. In addition, ConKI uses a hierarchical contrastive learning procedure performed between knowledge types within every single modality, across modalities within each sample, and across samples to facilitate the effective learning of the proposed representations, hence improving multimodal sentiment predictions. The experiments on three popular multimodal sentiment analysis benchmarks show that ConKI outperforms all prior methods on a variety of performance metrics.
Medical image segmentation of gadolinium enhancement magnetic resonance imaging (GE MRI) is an important task in clinical applications. However, manual annotation is time-consuming and requires specialized expertise. Semi-supervised segmentation methods that leverage both labeled and unlabeled data have shown promise, with contrastive learning emerging as a particularly effective approach. In this paper, we propose a contrastive learning strategy of foreground and background representations for semi-supervised 3D medical image segmentation (FBA-Net). Specifically, we leverage the contrastive loss to learn representations of both the foreground and background regions in the images. By training the network to distinguish between foreground-background pairs, we aim to learn a representation that can effectively capture the anatomical structures of interest. Experiments on three medical segmentation datasets demonstrate state-of-the-art performance. Notably, our method achieves a Dice score of 91.31% with only 20% labeled data, which is remarkably close to the 91.62% score of the fully supervised method that uses 100% labeled data on the left atrium dataset. Our framework has the potential to advance the field of semi-supervised 3D medical image segmentation and enable more efficient and accurate analysis of medical images with a limited amount of annotated labels.
Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the Generalized Out-of-distribution Fault Diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple faults diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.
We propose Unsupervised Episode Generation method called Neighbors as Queries (NaQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing so enables full utilization of the information of all nodes in a graph, which is not possible in current supervised meta-learning methods for FSNC due to the label-scarcity problem. In addition, unlike unsupervised Graph Contrastive Learning (GCL) methods that overlook the downstream task to be solved at the training phase resulting in vulnerability to class imbalance of a graph, we adopt the episodic learning framework that allows the model to be aware of the downstream task format, i.e., FSNC. The proposed NaQ is a simple but effective unsupervised episode generation method that randomly samples nodes from a graph to make a support set, followed by similarity-based sampling of nodes to make the corresponding query set. Since NaQ is model-agnostic, any existing supervised graph meta-learning methods can be trained in an unsupervised manner, while not sacrificing much of their performance or sometimes even improving them. Extensive experimental results demonstrate the effectiveness of our proposed unsupervised episode generation method for graph meta-learning towards the FSNC task. Our code is available at: https://github.com/JhngJng/NaQ-PyTorch.
Seismic intensity prediction from early or initial seismic waves received by a few seismic stations can enhance Earthquake Early Warning (EEW) systems, particularly in ground motion-based approaches like PLUM. While many operational EEW systems currently utilize point-source-based models that estimate the warning area based on magnitude and distance measures, direct intensity prediction offers a potential improvement in accuracy and reliability. In this paper, we propose a novel deep learning approach, Seismic Contrastive Graph Neural Network (SC-GNN), for highly accurate seismic intensity prediction using a small portion of initial seismic waveforms from a few seismic stations. The SC-GNN consists of two key components: (i) a graph neural network (GNN) to propagate spatiotemporal information through a graph-like structure representing seismic station distribution and wave propagation, and (ii) a self-supervised contrastive learning component to train the network with larger time windows and enable predictions using shorter initial waveforms. The efficacy of our approach is demonstrated through experiments on three real-world seismic datasets, where it shows superior performance over existing techniques, including a significant reduction in mean squared error (MSE) and the lowest standard deviation of error, indicating its robustness, reliability, and strong positive relationship between predicted and actual values. Notably, the SC-GNN model maintains superior performance even with 5s input waveforms, making it especially suitable for enhancing EEW applications.
Accurate customer lifetime value (LTV) prediction can help service providers optimize their marketing policies in customer-centric applications. However, the heavy sparsity of consumption events and the interference of data variance and noise obstruct LTV estimation. Many existing LTV prediction methods directly train a single-view LTV predictor on consumption samples, which may yield inaccurate and even biased knowledge extraction. In this paper, we propose a contrastive multi-view framework for LTV prediction, which is a plug-and-play solution compatible with various backbone models. It synthesizes multiple heterogeneous LTV regressors with complementary knowledge to improve model robustness and captures sample relatedness via contrastive learning to mitigate the dependency on data abundance. Concretely, we use a decomposed scheme that converts the LTV prediction problem into a combination of estimating consumption probability and payment amount. To alleviate the impact of noisy data on model learning, we propose a multi-view framework that jointly optimizes multiple types of regressors with diverse characteristics and advantages to encode and fuse comprehensive knowledge. To fully exploit the potential of limited training samples, we propose a hybrid contrastive learning method to help capture the relatedness between samples in both classification and regression tasks. We conduct extensive experiments on a real-world game LTV prediction dataset and the results validate the effectiveness of our method. We have deployed our solution online in Huawei's mobile game center and achieved 32.26% of total payment amount gains.
Contrastive learning has gained popularity due to its robustness with good feature representation performance. However, cosine distance, the commonly used similarity metric in contrastive learning, is not well suited to represent the distance between two data points, especially on a nonlinear feature manifold. Inspired by manifold learning, we propose a novel extension of contrastive learning that leverages geodesic distance between features as a similarity metric for histopathology whole slide image classification. To reduce the computational overhead in manifold learning, we propose geodesic-distance-based feature clustering for efficient contrastive loss evaluation using prototypes without time-consuming pairwise feature similarity comparison. The efficacy of the proposed method is evaluated on two real-world histopathology image datasets. Results demonstrate that our method outperforms state-of-the-art cosine-distance-based contrastive learning methods.
Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC method proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to force the generated captions to distinguish between the target image and the reference image. To ensure Ref-DIC models really perceive the unique objects (or attributes) in target images, we propose two new Ref-DIC benchmarks and develop a Transformer-based Ref-DIC baseline TransDIC. The model only extracts visual features from the target image, but also encodes the differences between objects in the target and reference images. Taking one step further, we propose a stronger TransDIC++, which consists of an extra contrastive learning module to make full use of the reference images. This new module is model-agnostic, which can be easily incorporated into various Ref-DIC architectures. Finally, for more trustworthy benchmarking, we propose a new evaluation metric named DisCIDEr for Ref-DIC, which evaluates both the accuracy and distinctiveness of the generated captions. Experimental results demonstrate that our TransDIC++ can generate distinctive captions. Besides, it outperforms several state-of-the-art models on the two new benchmarks over different metrics.
Self-supervised learning converts raw perceptual data such as images to a compact space where simple Euclidean distances measure meaningful variations in data. In this paper, we extend this formulation by adding additional geometric structure to the embedding space by enforcing transformations of input space to correspond to simple (i.e., linear) transformations of embedding space. Specifically, in the contrastive learning setting, we introduce an equivariance objective and theoretically prove that its minima forces augmentations on input space to correspond to rotations on the spherical embedding space. We show that merely combining our equivariant loss with a non-collapse term results in non-trivial representations, without requiring invariance to data augmentations. Optimal performance is achieved by also encouraging approximate invariance, where input augmentations correspond to small rotations. Our method, CARE: Contrastive Augmentation-induced Rotational Equivariance, leads to improved performance on downstream tasks, and ensures sensitivity in embedding space to important variations in data (e.g., color) that standard contrastive methods do not achieve. Code is available at https://github.com/Sharut/CARE.
Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GCL) based methods specifically suffer from adversarial attacks due to their inherent design that highly depends on the self-supervision signals derived from the original graph, which however already contains noise when the graph is attacked. To achieve adversarial robustness against such attacks, existing methods adopt adversarial training (AT) to the GCL framework, which considers the attacked graph as an augmentation under the GCL framework. However, we find that existing adversarially trained GCL methods achieve robustness at the expense of not being able to preserve the node feature similarity. In this paper, we propose a similarity-preserving adversarial graph contrastive learning (SP-AGCL) framework that contrasts the clean graph with two auxiliary views of different properties (i.e., the node similarity-preserving view and the adversarial view). Extensive experiments demonstrate that SP-AGCL achieves a competitive performance on several downstream tasks, and shows its effectiveness in various scenarios, e.g., a network with adversarial attacks, noisy labels, and heterophilous neighbors. Our code is available at https://github.com/yeonjun-in/torch-SP-AGCL.
The efficient utilization of wind power by wind turbines relies on the ability of their pitch systems to adjust blade pitch angles in response to varying wind speeds. However, the presence of multiple health conditions in the pitch system due to the long-term wear and tear poses challenges in accurately classifying them, thus increasing the maintenance cost of wind turbines or even damaging them. This paper proposes a novel method based on hard sample mining-enabled supervised contrastive learning (HSMSCL) to address this problem. The proposed method employs cosine similarity to identify hard samples and subsequently, leverages supervised contrastive learning to learn more discriminative representations by constructing hard sample pairs. Furthermore, the hard sample mining framework in the proposed method also constructs hard samples with learned representations to make the training process of the multilayer perceptron (MLP) more challenging and make it a more effective classifier. The proposed approach progressively improves the fault diagnosis model by introducing hard samples in the SCL and MLP phases, thus enhancing its performance in complex multi-class fault diagnosis tasks. To evaluate the effectiveness of the proposed method, two real datasets comprising wind turbine pitch system cog belt fracture data are utilized. The fault diagnosis performance of the proposed method is compared against existing methods, and the results demonstrate its superior performance. The proposed approach exhibits significant improvements in fault diagnosis performance, providing promising prospects for enhancing the reliability and efficiency of wind turbine pitch system fault diagnosis.
In this paper, we investigate the effectiveness of contrastive learning methods for predicting grasp outcomes in an unsupervised manner. By utilizing a publicly available dataset, we demonstrate that contrastive learning methods perform well on the task of grasp outcomes prediction. Specifically, the dynamic-dictionary-based method with the momentum updating technique achieves a satisfactory accuracy of 81.83% using data from one single tactile sensor, outperforming other unsupervised methods. Our results reveal the potential of contrastive learning methods for applications in the field of robot grasping and highlight the importance of accurate grasp prediction for achieving stable grasps.
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant regions, which limits their performance. In this paper, we focus on representation learning for semi-supervised learning, by developing a novel Multi-Scale Cross Supervised Contrastive Learning (MCSC) framework, to segment structures in medical images. We jointly train CNN and Transformer models, regularising their features to be semantically consistent across different scales. Our approach contrasts multi-scale features based on ground-truth and cross-predicted labels, in order to extract robust feature representations that reflect intra- and inter-slice relationships across the whole dataset. To tackle class imbalance, we take into account the prevalence of each class to guide contrastive learning and ensure that features adequately capture infrequent classes. Extensive experiments on two multi-structure medical segmentation datasets demonstrate the effectiveness of MCSC. It not only outperforms state-of-the-art semi-supervised methods by more than 3.0% in Dice, but also greatly reduces the performance gap with fully supervised methods.
Self-supervised learning of deep neural networks has become a prevalent paradigm for learning representations that transfer to a variety of downstream tasks. Similar to proposed models of the ventral stream of biological vision, it is observed that these networks lead to a separation of category manifolds in the representations of the penultimate layer. Although this observation matches the manifold hypothesis of representation learning, current self-supervised approaches are limited in their ability to explicitly model this manifold. Indeed, current approaches often only apply augmentations from a pre-specified set of "positive pairs" during learning. In this work, we propose a contrastive learning approach that directly models the latent manifold using Lie group operators parameterized by coefficients with a sparsity-promoting prior. A variational distribution over these coefficients provides a generative model of the manifold, with samples which provide feature augmentations applicable both during contrastive training and downstream tasks. Additionally, learned coefficient distributions provide a quantification of which transformations are most likely at each point on the manifold while preserving identity. We demonstrate benefits in self-supervised benchmarks for image datasets, as well as a downstream semi-supervised task. In the former case, we demonstrate that the proposed methods can effectively apply manifold feature augmentations and improve learning both with and without a projection head. In the latter case, we demonstrate that feature augmentations sampled from learned Lie group operators can improve classification performance when using few labels.
The common standard for quality evaluation of automatic speech recognition (ASR) systems is reference-based metrics such as the Word Error Rate (WER), computed using manual ground-truth transcriptions that are time-consuming and expensive to obtain. This work proposes a multi-language referenceless quality metric, which allows comparing the performance of different ASR models on a speech dataset without ground truth transcriptions. To estimate the quality of ASR hypotheses, a pre-trained language model (LM) is fine-tuned with contrastive learning in a self-supervised learning manner. In experiments conducted on several unseen test datasets consisting of outputs from top commercial ASR engines in various languages, the proposed referenceless metric obtains a much higher correlation with WER scores and their ranks than the perplexity metric from the state-of-art multi-lingual LM in all experiments, and also reduces WER by more than $7\%$ when used for ensembling hypotheses. The fine-tuned model and experiments are made available for the reproducibility: https://github.com/aixplain/NoRefER
Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks, aiming to enrich the agent's learned representations with control-relevant information for future state prediction. However, these objectives are often insufficient to learn representations that can represent the optimal policy or value function, and they often consider tasks with small, abstract discrete action spaces and thus overlook the importance of action representation learning in continuous control. In this paper, we introduce TACO: Temporal Action-driven Contrastive Learning, a simple yet powerful temporal contrastive learning approach that facilitates the concurrent acquisition of latent state and action representations for agents. TACO simultaneously learns a state and an action representation by optimizing the mutual information between representations of current states paired with action sequences and representations of the corresponding future states. Theoretically, TACO can be shown to learn state and action representations that encompass sufficient information for control, thereby improving sample efficiency. For online RL, TACO achieves 40% performance boost after one million environment interaction steps on average across nine challenging visual continuous control tasks from Deepmind Control Suite. In addition, we show that TACO can also serve as a plug-and-play module adding to existing offline visual RL methods to establish the new state-of-the-art performance for offline visual RL across offline datasets with varying quality.