In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of information and establishing the relationship between them. One is the global shape of an object, and the other is the local structures of it. However, few existing studies in point cloud representation learning explored how to learn both global shapes and local-to-global relationships without a specified network architecture. Inspired by how human beings understand the world, we utilize knowledge distillation to learn both global shape information and the relationship between global shape and local structures. At the same time, we combine contrastive learning with knowledge distillation to make the teacher network be better updated. Our method achieves the state-of-the-art performance on linear classification and multiple other downstream tasks. Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method. Our code will be released soon.
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning, heavily depends on both clean and sufficient labeled data, which is always difficult to acquire. Noisy unlabeled data, on the other hand, also provides valuable information that can be exploited using self-supervised training methods. In this work, we investigate how to pretrain speaker recognition models by leveraging dialogues between customers and smart-speaker devices. However, the supervisory information in such dialogues is inherently noisy, as multiple speakers may speak to a device in the course of the same dialogue. To address this issue, we propose an effective rejection mechanism that selectively learns from dialogues based on their acoustic homogeneity. Both reconstruction-based and contrastive-learning-based self-supervised methods are compared. Experiments demonstrate that the proposed method provides significant performance improvements, superior to earlier work. Dialogue pretraining when combined with the rejection mechanism yields 27.10% equal error rate (EER) reduction in speaker recognition, compared to a model without self-supervised pretraining.
Ground deformation measured from Interferometric Synthetic Aperture Radar (InSAR) data is considered a sign of volcanic unrest, statistically linked to a volcanic eruption. Recent studies have shown the potential of using Sentinel-1 InSAR data and supervised deep learning (DL) methods for the detection of volcanic deformation signals, towards global volcanic hazard mitigation. However, detection accuracy is compromised from the lack of labelled data and class imbalance. To overcome this, synthetic data are typically used for finetuning DL models pre-trained on the ImageNet dataset. This approach suffers from poor generalisation on real InSAR data. This letter proposes the use of self-supervised contrastive learning to learn quality visual representations hidden in unlabeled InSAR data. Our approach, based on the SimCLR framework, provides a solution that does not require a specialized architecture nor a large labelled or synthetic dataset. We show that our self-supervised pipeline achieves higher accuracy with respect to the state-of-the-art methods, and shows excellent generalisation even for out-of-distribution test data. Finally, we showcase the effectiveness of our approach for detecting the unrest episodes preceding the recent Icelandic Fagradalsfjall volcanic eruption.
Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning framework suitable for hyperspectral images that are inherently challenging to annotate. The proposed framework architecture leverages cross-domain CNN, allowing for learning representations from different hyperspectral images with varying spectral characteristics and no pixel-level annotation. In the framework, cross-domain representations are learned via contrastive learning where neighboring spectral vectors in the same image are clustered together in a common representation space encompassing multiple hyperspectral images. In contrast, spectral vectors in different hyperspectral images are separated into distinct clusters in the space. To verify that the learned representation through contrastive learning is effectively transferred into a downstream task, we perform a classification task on hyperspectral images. The experimental results demonstrate the advantage of the proposed self-supervised representation over models trained from scratch or other transfer learning methods.
Video Instance Segmentation (VIS) is a task that simultaneously requires classification, segmentation, and instance association in a video. Recent VIS approaches rely on sophisticated pipelines to achieve this goal, including RoI-related operations or 3D convolutions. In contrast, we present a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head. To improve instance association accuracy, a novel bi-directional spatio-temporal contrastive learning strategy for tracking embedding across frames is proposed. Moreover, an instance-wise temporal consistency scheme is utilized to produce temporally coherent results. Experiments conducted on the YouTube-VIS-2019, YouTube-VIS-2021, and OVIS-2021 datasets validate the effectiveness and efficiency of the proposed method. We hope the proposed framework can serve as a simple and strong alternative for many other instance-level video association tasks.
Graph contrastive learning (GCL) has emerged as a dominant technique for graph representation learning which maximizes the mutual information between paired graph augmentations that share the same semantics. Unfortunately, it is difficult to preserve semantics well during augmentations in view of the diverse nature of graph data. Currently, data augmentations in GCL that are designed to preserve semantics broadly fall into three unsatisfactory ways. First, the augmentations can be manually picked per dataset by trial-and-errors. Second, the augmentations can be selected via cumbersome search. Third, the augmentations can be obtained by introducing expensive domain-specific knowledge as guidance. All of these limit the efficiency and more general applicability of existing GCL methods. To circumvent these crucial issues, we propose a \underline{Sim}ple framework for \underline{GRA}ph \underline{C}ontrastive l\underline{E}arning, \textbf{SimGRACE} for brevity, which does not require data augmentations. Specifically, we take original graph as input and GNN model with its perturbed version as two encoders to obtain two correlated views for contrast. SimGRACE is inspired by the observation that graph data can preserve their semantics well during encoder perturbations while not requiring manual trial-and-errors, cumbersome search or expensive domain knowledge for augmentations selection. Also, we explain why SimGRACE can succeed. Furthermore, we devise adversarial training scheme, dubbed \textbf{AT-SimGRACE}, to enhance the robustness of graph contrastive learning and theoretically explain the reasons. Albeit simple, we show that SimGRACE can yield competitive or better performance compared with state-of-the-art methods in terms of generalizability, transferability and robustness, while enjoying unprecedented degree of flexibility and efficiency.
Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims at minimizing distances between positive pairs. For high performance Siamese representation learning, one of the keys is to design good contrastive pairs. Most previous works simply apply random sampling to make different crops of the same image, which overlooks the semantic information that may degrade the quality of views. In this work, we propose ContrastiveCrop, which could effectively generate better crops for Siamese representation learning. Firstly, a semantic-aware object localization strategy is proposed within the training process in a fully unsupervised manner. This guides us to generate contrastive views which could avoid most false positives (i.e., object vs. background). Moreover, we empirically find that views with similar appearances are trivial for the Siamese model training. Thus, a center-suppressed sampling is further designed to enlarge the variance of crops. Remarkably, our method takes a careful consideration of positive pairs for contrastive learning with negligible extra training overhead. As a plug-and-play and framework-agnostic module, ContrastiveCrop consistently improves SimCLR, MoCo, BYOL, SimSiam by 0.4% ~ 2.0% classification accuracy on CIFAR-10, CIFAR-100, Tiny ImageNet and STL-10. Superior results are also achieved on downstream detection and segmentation tasks when pre-trained on ImageNet-1K.
The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while randomly mismatched pairs as negatives. However, these negative pairs may contain semantically matched audio-visual information. Thus, these semantically correlated pairs, "hard positives", are mistakenly grouped as negatives. Our key contribution is showing that hard positives can give similar response maps to the corresponding pairs. Our approach incorporates these hard positives by adding their response maps into a contrastive learning objective directly. We demonstrate the effectiveness of our approach on VGG-SS and SoundNet-Flickr test sets, showing favorable performance to the state-of-the-art methods.
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. The conventional DA strategy is to align the feature distributions of the two domains. Recently, increasing researches have focused on self-training or other semi-supervised algorithms to explore the data structure of the target domain. However, the bulk of them depend largely on confident samples in order to build reliable pseudo labels, prototypes or cluster centers. Representing the target data structure in such a way would overlook the huge low-confidence samples, resulting in sub-optimal transferability that is biased towards the samples similar to the source domain. To overcome this issue, we propose a novel contrastive learning method by processing low-confidence samples, which encourages the model to make use of the target data structure through the instance discrimination process. To be specific, we create positive and negative pairs only using low-confidence samples, and then re-represent the original features with the classifier weights rather than directly utilizing them, which can better encode the task-specific semantic information. Furthermore, we combine cross-domain mixup to augment the proposed contrastive loss. Consequently, the domain gap can be well bridged through contrastive learning of intermediate representations across domains. We evaluate the proposed method in both unsupervised and semi-supervised DA settings, and extensive experimental results on benchmarks reveal that our method is effective and achieves state-of-the-art performance. The code can be found in https://github.com/zhyx12/MixLRCo.
Self-supervised learning of graph neural networks (GNNs) aims to learn an accurate representation of the graphs in an unsupervised manner, to obtain transferable representations of them for diverse downstream tasks. Predictive learning and contrastive learning are the two most prevalent approaches for graph self-supervised learning. However, they have their own drawbacks. While the predictive learning methods can learn the contextual relationships between neighboring nodes and edges, they cannot learn global graph-level similarities. Contrastive learning, while it can learn global graph-level similarities, its objective to maximize the similarity between two differently perturbed graphs may result in representations that cannot discriminate two similar graphs with different properties. To tackle such limitations, we propose a framework that aims to learn the exact discrepancy between the original and the perturbed graphs, coined as Discrepancy-based Self-supervised LeArning (D-SLA). Specifically, we create multiple perturbations of the given graph with varying degrees of similarity, and train the model to predict whether each graph is the original graph or the perturbed one. Moreover, we further aim to accurately capture the amount of discrepancy for each perturbed graph using the graph edit distance. We validate our D-SLA on various graph-related downstream tasks, including molecular property prediction, protein function prediction, and link prediction tasks, on which ours largely outperforms relevant baselines.
This paper tackles the problem of subject adaptive EEG-based visual recognition. Its goal is to accurately predict the categories of visual stimuli based on EEG signals with only a handful of samples for the target subject during training. The key challenge is how to appropriately transfer the knowledge obtained from abundant data of source subjects to the subject of interest. To this end, we introduce a novel method that allows for learning subject-independent representation by increasing the similarity of features sharing the same class but coming from different subjects. With the dedicated sampling principle, our model effectively captures the common knowledge shared across different subjects, thereby achieving promising performance for the target subject even under harsh problem settings with limited data. Specifically, on the EEG-ImageNet40 benchmark, our model records the top-1 / top-3 test accuracy of 72.6% / 91.6% when using only five EEG samples per class for the target subject. Our code is available at https://github.com/DeepBCI/Deep-BCI/tree/master/1_Intelligent_BCI/Inter_Subject_Contrastive_Learning_for_EEG.
Users' interactions with items are driven by various intents (e.g., preparing for holiday gifts, shopping for fishing equipment, etc.).However, users' underlying intents are often unobserved/latent, making it challenging to leverage such latent intents forSequentialrecommendation(SR). To investigate the benefits of latent intents and leverage them effectively for recommendation, we proposeIntentContrastiveLearning(ICL), a general learning paradigm that leverages a latent intent variable into SR. The core idea is to learn users' intent distribution functions from unlabeled user behavior sequences and optimize SR models with contrastive self-supervised learning (SSL) by considering the learned intents to improve recommendation. Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering. We propose to leverage the learned intents into SR models via contrastive SSL, which maximizes the agreement between a view of sequence and its corresponding intent. The training is alternated between intent representation learning and the SR model optimization steps within the generalized expectation-maximization (EM) framework. Fusing user intent information into SR also improves model robustness. Experiments conducted on four real-world datasets demonstrate the superiority of the proposed learning paradigm, which improves performance, and robustness against data sparsity and noisy interaction issues.
With the recent boom of video-based social platforms (e.g., YouTube and TikTok), video retrieval using sentence queries has become an important demand and attracts increasing research attention. Despite the decent performance, existing text-video retrieval models in vision and language communities are impractical for large-scale Web search because they adopt brute-force search based on high-dimensional embeddings. To improve efficiency, Web search engines widely apply vector compression libraries (e.g., FAISS) to post-process the learned embeddings. Unfortunately, separate compression from feature encoding degrades the robustness of representations and incurs performance decay. To pursue a better balance between performance and efficiency, we propose the first quantized representation learning method for cross-view video retrieval, namely Hybrid Contrastive Quantization (HCQ). Specifically, HCQ learns both coarse-grained and fine-grained quantizations with transformers, which provide complementary understandings for texts and videos and preserve comprehensive semantic information. By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels. This hybrid-grained learning strategy serves as strong supervision on the cross-view video quantization model, where contrastive learning at different levels can be mutually promoted. Extensive experiments on three Web video benchmark datasets demonstrate that HCQ achieves competitive performance with state-of-the-art non-compressed retrieval methods while showing high efficiency in storage and computation. Code and configurations are available at https://github.com/gimpong/WWW22-HCQ.
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and negative pairs. However, it is not trivial to build reasonable pairs for a segmentation task in an unsupervised way. In this work, we propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Our framework consists of two principles: unsupervised over-segmentation as a pre-train task using mutual information maximization and boundary-aware preserving learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.
Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in e-commerce using product offers from different e-shops. More specifically, we employ a supervised contrastive learning technique to pre-train a Transformer encoder which is afterward fine-tuned for the matching task using pair-wise training data. We further propose a source-aware sampling strategy that enables contrastive learning to be applied for use cases in which the training data does not contain product identifiers. We show that applying supervised contrastive pre-training in combination with source-aware sampling significantly improves the state-of-the-art performance on several widely used benchmarks: For Abt-Buy, we reach an F1-score of 94.29 (+3.24 compared to the previous state-of-the-art), for Amazon-Google 79.28 (+ 3.7). For WDC Computers datasets, we reach improvements between +0.8 and +8.84 in F1-score depending on the training set size. Further experiments with data augmentation and self-supervised contrastive pre-training show that the former can be helpful for smaller training sets while the latter leads to a significant decline in performance due to inherent label noise. We thus conclude that contrastive pre-training has a high potential for product matching use cases in which explicit supervision is available.
The quality assessment (QA) of restored low light images is an important tool for benchmarking and improving low light restoration (LLR) algorithms. While several LLR algorithms exist, the subjective perception of the restored images has been much less studied. Challenges in capturing aligned low light and well-lit image pairs and collecting a large number of human opinion scores of quality for training, warrant the design of unsupervised (or opinion unaware) no-reference (NR) QA methods. This work studies the subjective perception of low light restored images and their unsupervised NR QA. Our contributions are two-fold. We first create a dataset of restored low light images using various LLR methods, conduct a subjective QA study and benchmark the performance of existing QA methods. We then present a self-supervised contrastive learning technique to extract distortion aware features from the restored low light images. We show that these features can be effectively used to build an opinion unaware image quality analyzer. Detailed experiments reveal that our unsupervised NR QA model achieves state-of-the-art performance among all such quality measures for low light restored images.
Deep learning has been actively studied for time series forecasting, and the mainstream paradigm is based on the end-to-end training of neural network architectures, ranging from classical LSTM/RNNs to more recent TCNs and Transformers. Motivated by the recent success of representation learning in computer vision and natural language processing, we argue that a more promising paradigm for time series forecasting, is to first learn disentangled feature representations, followed by a simple regression fine-tuning step -- we justify such a paradigm from a causal perspective. Following this principle, we propose a new time series representation learning framework for time series forecasting named CoST, which applies contrastive learning methods to learn disentangled seasonal-trend representations. CoST comprises both time domain and frequency domain contrastive losses to learn discriminative trend and seasonal representations, respectively. Extensive experiments on real-world datasets show that CoST consistently outperforms the state-of-the-art methods by a considerable margin, achieving a 21.3% improvement in MSE on multivariate benchmarks. It is also robust to various choices of backbone encoders, as well as downstream regressors. Code is available at https://github.com/salesforce/CoST.
This work introduces a dataset for large-scale instance-level recognition in the domain of artworks. The proposed benchmark exhibits a number of different challenges such as large inter-class similarity, long tail distribution, and many classes. We rely on the open access collection of The Met museum to form a large training set of about 224k classes, where each class corresponds to a museum exhibit with photos taken under studio conditions. Testing is primarily performed on photos taken by museum guests depicting exhibits, which introduces a distribution shift between training and testing. Testing is additionally performed on a set of images not related to Met exhibits making the task resemble an out-of-distribution detection problem. The proposed benchmark follows the paradigm of other recent datasets for instance-level recognition on different domains to encourage research on domain independent approaches. A number of suitable approaches are evaluated to offer a testbed for future comparisons. Self-supervised and supervised contrastive learning are effectively combined to train the backbone which is used for non-parametric classification that is shown as a promising direction. Dataset webpage: http://cmp.felk.cvut.cz/met/
A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning techniques have emerged that can learn good features from the data without requiring any labels. In this paper, we extend this line of research and present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices worn by a user to learn high-quality features of the data. A key insight that underpins the design of ColloSSL is that unlabeled sensor datasets simultaneously captured by multiple devices can be viewed as natural transformations of each other, and leveraged to generate a supervisory signal for representation learning. We present three technical innovations to extend conventional self-supervised learning algorithms to a multi-device setting: a Device Selection approach which selects positive and negative devices to enable contrastive learning, a Contrastive Sampling algorithm which samples positive and negative examples in a multi-device setting, and a loss function called Multi-view Contrastive Loss which extends standard contrastive loss to a multi-device setting. Our experimental results on three multi-device datasets show that ColloSSL outperforms both fully-supervised and semi-supervised learning techniques in majority of the experiment settings, resulting in an absolute increase of upto 7.9% in F_1 score compared to the best performing baselines. We also show that ColloSSL outperforms the fully-supervised methods in a low-data regime, by just using one-tenth of the available labeled data in the best case.
Text style transfer is a challenging text generation problem, which aims at altering the style of a given sentence to a target one while keeping its content unchanged. Since there is a natural scarcity of parallel datasets, recent works mainly focus on solving the problem in an unsupervised manner. However, previous gradient-based works generally suffer from the deficiencies as follows, namely: (1) Content migration. Previous approaches lack explicit modeling of content invariance and are thus susceptible to content shift between the original sentence and the transferred one. (2) Style misclassification. A natural drawback of the gradient-guided approaches is that the inference process is homogeneous with a line of adversarial attack, making latent optimization easily becomes an attack to the classifier due to misclassification. This leads to difficulties in achieving high transfer accuracy. To address the problems, we propose a novel gradient-guided model through a contrastive paradigm for text style transfer, to explicitly gather similar semantic sentences, and to design a siamese-structure based style classifier for alleviating such two issues, respectively. Experiments on two datasets show the effectiveness of our proposed approach, as compared to the state-of-the-arts.