In this work, we study a new image annotation task named Extractive Tags Summarization (ETS). The goal is to extract important tags from the context lying in an image and its corresponding tags. We adjust some state-of-the-art deep learning models to utilize both visual and textual information. Our proposed solution consists of different widely used blocks like convolutional and self-attention layers, together with a novel idea of combining auxiliary loss functions and the gating mechanism to glue and elevate these fundamental components and form a unified architecture. Besides, we introduce a loss function that aims to reduce the imbalance of the training data and a simple but effective data augmentation technique dedicated to alleviates the effect of outliers on the final results. Last but not least, we explore an unsupervised pre-training strategy to further boost the performance of the model by making use of the abundant amount of available unlabeled data. Our model shows the good results as 90% $F_\text{1}$ score on the public NUS-WIDE benchmark, and 50% $F_\text{1}$ score on a noisy large-scale real-world private dataset. Source code for reproducing the experiments is publicly available at: https://github.com/pixta-dev/labteam
This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to cleaning recordings of a test-time speaker is limited to a few seconds, but noisy recordings of the speaker are abundant. We develop a simple contrastive learning procedure which treats the abundant noisy data as makeshift training targets through pairwise noise injection: the model is pretrained to maximize agreement between pairs of differently deformed identical utterances and to minimize agreement between pairs of similarly deformed nonidentical utterances. Our experiments compare the proposed pretraining approach with two baseline alternatives: speaker-agnostic fully-supervised pretraining, and speaker-specific self-supervised pretraining without contrastive loss terms. Of all three approaches, the proposed method using contrastive mixtures is found to be most robust to model compression (using 85% fewer parameters) and reduced clean speech (requiring only 3 seconds).
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural Networks (ConvNets) which require a large amount of training data paired with densely annotated labels. Depth annotation tasks are both expensive and inefficient, so it is inevitable to leverage RGB images which can be collected very easily to boost the performance of ConvNets without depth labels. However, most self-supervised learning algorithms are focused on capturing the semantic information of images to improve the performance in classification or object detection, not in depth estimation. In this paper, we show that existing self-supervised methods do not perform well on depth estimation and propose a gradient-based self-supervised learning algorithm with momentum contrastive loss to help ConvNets extract the geometric information with unlabeled images. As a result, the network can estimate the depth map accurately with a relatively small amount of annotated data. To show that our method is independent of the model structure, we evaluate our method with two different monocular depth estimation algorithms. Our method outperforms the previous state-of-the-art self-supervised learning algorithms and shows the efficiency of labeled data in triple compared to random initialization on the NYU Depth v2 dataset.
Diffusion-weighted magnetic resonance imaging (DWI) is the only noninvasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant additive noise in DWI data which must be suppressed before subsequent microstructure analysis. We introduce a self-supervised learning method for denoising DWI data, Patch2Self, which uses the entire volume to learn a full-rank locally linear denoiser for that volume. By taking advantage of the oversampled q-space of DWI data, Patch2Self can separate structure from noise without requiring an explicit model for either. We demonstrate the effectiveness of Patch2Self via quantitative and qualitative improvements in microstructure modeling, tracking (via fiber bundle coherency) and model estimation relative to other unsupervised methods on real and simulated data.
This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent progress in BERT-based language models for ABSA. However, it is not clear how the general proxy task of (masked) language model trained on unlabeled corpus without annotations of aspects or opinions can provide important features for downstream tasks in ABSA. By leveraging the annotated datasets in ABSA, we investigate both the attentions and the learned representations of BERT pre-trained on reviews. We found that BERT uses very few self-attention heads to encode context words (such as prepositions or pronouns that indicating an aspect) and opinion words for an aspect. Most features in the representation of an aspect are dedicated to the fine-grained semantics of the domain (or product category) and the aspect itself, instead of carrying summarized opinions from its context. We hope this investigation can help future research in improving self-supervised learning, unsupervised learning and fine-tuning for ABSA. The pre-trained model and code can be found at https://github.com/howardhsu/BERT-for-RRC-ABSA.
Recently proposed neural architecture search (NAS) algorithms adopt neural predictors to accelerate the architecture search. The capability of neural predictors to accurately predict the performance metrics of neural architecture is critical to NAS, and the acquisition of training datasets for neural predictors is time-consuming. How to obtain a neural predictor with high prediction accuracy using a small amount of training data is a central problem to neural predictor-based NAS. Here, we firstly design a new architecture encoding scheme that overcomes the drawbacks of existing vector-based architecture encoding schemes to calculate the graph edit distance of neural architectures. To enhance the predictive performance of neural predictors, we devise two self-supervised learning methods from different perspectives to pre-train the architecture embedding part of neural predictors to generate a meaningful representation of neural architectures. The first one is to train a carefully designed two branch graph neural network model to predict the graph edit distance of two input neural architectures. The second method is inspired by the prevalently contrastive learning, and we present a new contrastive learning algorithm that utilizes a central feature vector as a proxy to contrast positive pairs against negative pairs. Experimental results illustrate that the pre-trained neural predictors can achieve comparable or superior performance compared with their supervised counterparts with several times less training samples. We achieve state-of-the-art performance on the NASBench-101 and NASBench201 benchmarks when integrating the pre-trained neural predictors with an evolutionary NAS algorithm.
Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that they could capture "better" temporal information. However, there exist setting differences among them and it is hard to conclude which is better. It would be much more convincing in comparison if these methods have reached as closer to their performance limits as possible. In this paper, we start from one pretext-task baseline, exploring how far it can go by combining it with contrastive learning, data pre-processing, and data augmentation. A proper setting has been found from extensive experiments, with which huge improvements over the baselines can be achieved, indicating a joint optimization framework can boost both pretext task and contrastive learning. We denote the joint optimization framework as Pretext-Contrastive Learning (PCL). The other two pretext task baselines are used to validate the effectiveness of PCL. And we can easily outperform current state-of-the-art methods in the same training manner, showing the effectiveness and the generality of our proposal. It is convenient to treat PCL as a standard training strategy and apply it to many other works in self-supervised video feature learning.
Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice. There have been several proposals to alleviate this issue with, for instance, self-supervised learning techniques, but they still require human-annotated corpora. In this work, we explore the unsupervised learning paradigm which can potentially work with unlabeled text corpora that are cheaper and easier to obtain. Our model builds upon the recent work on Noisy Student Training, a semi-supervised learning approach that extends the idea of self-training. Experimental results on the commonly used English Switchboard test set show that our approach achieves competitive performance compared to the previous state-of-the-art supervised systems using contextualized word embeddings (e.g. BERT and ELECTRA).
Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augmentations on multiple datasets, in four different settings: semi-supervised, unsupervised, and transfer learning as well as adversarial attacks. The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, our GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. We also investigate the impact of parameterized graph augmentation extents and patterns, and observe further performance gains in preliminary experiments. Our codes are available at https://github.com/Shen-Lab/GraphCL.
Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the available models and research have been conducted for English. In this work, we introduce BARThez, the first large-scale pretrained seq2seq model for French. Being based on BART, BARThez is particularly well-suited for generative tasks. We evaluate BARThez on five discriminative tasks from the FLUE benchmark and two generative tasks from a novel summarization dataset, OrangeSum, that we created for this research. We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT. We also continue the pretraining of a multilingual BART on BARThez' corpus, and show our resulting model, mBARThez, to significantly boost BARThez' generative performance. Code, data and models are publicly available.
Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects. It would be natural to obtain part mobility from the continuous part motion of 3D objects. In this study, we introduce a self-supervised method for segmenting motion parts and predicting their motion attributes from a point cloud sequence representing a dynamic object. To sufficiently utilize spatiotemporal information from the point cloud sequence, we generate trajectories by using correlations among successive frames of the sequence instead of directly processing the point clouds. We propose a novel neural network architecture called PointRNN to learn feature representations of trajectories along with their part rigid motions. We evaluate our method on various tasks including motion part segmentation, motion axis prediction and motion range estimation. The results demonstrate that our method outperforms previous techniques on both synthetic and real datasets. Moreover, our method has the ability to generalize to new and unseen objects. It is important to emphasize that it is not required to know any prior shape structure, prior shape category information, or shape orientation. To the best of our knowledge, this is the first study on deep learning to extract part mobility from point cloud sequence of a dynamic object.
We propose a new approach for power control in wireless networks using self-supervised learning. We partition a multi-layer perceptron that takes as input the channel matrix and outputs the power control decisions into a backbone and a head, and we show how we can use contrastive learning to pre-train the backbone so that it produces similar embeddings at its output for similar channel matrices and vice versa, where similarity is defined in an information-theoretic sense by identifying the interference links that can be optimally treated as noise. The backbone and the head are then fine-tuned using a limited number of labeled samples. Simulation results show the effectiveness of the proposed approach, demonstrating significant gains over pure supervised learning methods in both sum-throughput and sample efficiency.
Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologies with 4M+ concepts. In contrast with previous pipeline-based hybrid systems, SapBERT offers an elegant one-model-for-all solution to the problem of medical entity linking (MEL), achieving a new state-of-the-art (SOTA) on six MEL benchmarking datasets. In the scientific domain, we achieve SOTA even without task-specific supervision. With substantial improvement over various domain-specific pretrained MLMs such as BioBERT, SciBERTand and PubMedBERT, our pretraining scheme proves to be both effective and robust.
Representation learning on user-item graph for recommendation has evolved from using single ID or interaction history to exploiting higher-order neighbors. This leads to the success of graph convolution networks (GCNs) for recommendation such as PinSage and LightGCN. Despite effectiveness, we argue that they suffer from two limitations: (1) high-degree nodes exert larger impact on the representation learning, deteriorating the recommendations of low-degree (long-tail) items; and (2) representations are vulnerable to noisy interactions, as the neighborhood aggregation scheme further enlarges the impact of observed edges. In this work, we explore self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation. The idea is to supplement the classical supervised task of recommendation with an auxiliary self-supervised task, which reinforces node representation learning via self-discrimination. Specifically, we generate multiple views of a node, maximizing the agreement between different views of the same node compared to that of other nodes. We devise three operators to generate the views -- node dropout, edge dropout, and random walk -- that change the graph structure in different manners. We term this new learning paradigm as \textit{Self-supervised Graph Learning} (SGL), implementing it on the state-of-the-art model LightGCN. Through theoretical analyses, we find that SGL has the ability of automatically mining hard negatives. Empirical studies on three benchmark datasets demonstrate the effectiveness of SGL, which improves the recommendation accuracy, especially on long-tail items, and the robustness against interaction noises. Our implementations are available at \url{https://github.com/wujcan/SGL}.
YouTube is an important source of news and entertainment worldwide, but the scale makes it challenging to study the ideas and topics being discussed on the platform. This paper presents new methods to discover and classify YouTube channels which enable the analysis of communities and categories on the platform using orders of magnitude more channels than have been used in previous studies. Instead of using channel and video data as features for classification as other researchers have, these methods use a self-supervised learning approach that leverages the public subscription pages of commenters. We test the classification method on the task of predicting the political lean of YouTube news channels and find that it outperforms the previous best model on the task. Further experiments also show that there are important advantages to using commenter subscriptions to discover channels. The subscription data, along with an iterative approach, is applied to discover, to our current understanding, the most comprehensive set of English language socio-political YouTube channels yet to be analyzed. We experiment with predicting more fine grained political tags for channels using a previously annotated dataset and find that our model performs better than the average individual human reviewer for most of the top tags. This fine grained political tag model is then applied to the newly discovered English language socio-political channels to create a new dataset to analyze the amount of traffic going to different political content. The data shows that some tags, such as "Partisan Right" and "Conspiracy", are significantly under represented when looking only at the most popular socio-political channels. Through the use of our methods, we are able to get a much more accurate picture of the size of these communities on YouTube.
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric characteristics, we propose to borrow self-supervised representation learning to facilitate geometric features discovery. To condense these features, we introduce an interpretable attention module, with the core of local maxima aggregation instead of fully automatic learning, whose mechanism is completely understandable and whose response map is physically reasonable. To the best of our knowledge, we are the first that perform self-supervised learning to discover geometric features. We conduct comprehensive experiments on three most popular datasets for vehicle ReID, i.e., VeRi-776, CityFlow-ReID, and VehicleID. We report our state-of-the-art (SOTA) performances and promising visualization results. We also show the excellent scalability of our approach on other ReID related tasks, i.e., person ReID and multi-target multi-camera (MTMC) vehicle tracking.
We prove a new upper bound on the generalization gap of classifiers that are obtained by first using self-supervision to learn a representation $r$ of the training data, and then fitting a simple (e.g., linear) classifier $g$ to the labels. Specifically, we show that (under the assumptions described below) the generalization gap of such classifiers tends to zero if $\mathsf{C}(g) \ll n$, where $\mathsf{C}(g)$ is an appropriately-defined measure of the simple classifier $g$'s complexity, and $n$ is the number of training samples. We stress that our bound is independent of the complexity of the representation $r$. We do not make any structural or conditional-independence assumptions on the representation-learning task, which can use the same training dataset that is later used for classification. Rather, we assume that the training procedure satisfies certain natural noise-robustness (adding small amount of label noise causes small degradation in performance) and rationality (getting the wrong label is not better than getting no label at all) conditions that widely hold across many standard architectures. We show that our bound is non-vacuous for many popular representation-learning based classifiers on CIFAR-10 and ImageNet, including SimCLR, AMDIM and MoCo.
We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of multimodal self-supervised learning also represent the linguistic and visual context, their encoders for different modalities are coupled. Thus they cannot incorporate visual information when encoding plain text alone. In this paper, we propose Multimodal Aligned Contrastive Decoupled learning (MACD) network. MACD forces the decoupled text encoder to represent the visual information via contrastive learning. Therefore, it embeds visual knowledge even for plain text inference. We conducted comprehensive experiments over plain text inference datasets (i.e. SNLI and STS-B). The unsupervised MACD even outperforms the fully-supervised BiLSTM and BiLSTM+ELMO on STS-B.
Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques can face a variety of visual conditions required by real-world environments. We propose a challenging benchmark that tests agents' visual generalization by adding graphical variety to existing continuous control domains. Our empirical analysis shows that current methods struggle to generalize across a diverse set of visual changes, and we examine the specific factors of variation that make these tasks difficult. We find that data augmentation techniques outperform self-supervised learning approaches and that more significant image transformations provide better visual generalization \footnote{The benchmark and our augmented actor-critic implementation are open-sourced @ https://github.com/QData/dmc_remastered)
Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the corresponding negatives pairs, one can train good visual representations without human annotations. This paper proposes Mix-up Contrast (MixCo), which extends the contrastive learning concept to semi-positives encoded from the mix-up of positive and negative images. MixCo aims to learn the relative similarity of representations, reflecting how much the mixed images have the original positives. We validate the efficacy of MixCo when applied to the recent self-supervised learning algorithms under the standard linear evaluation protocol on TinyImageNet, CIFAR10, and CIFAR100. In the experiments, MixCo consistently improves test accuracy. Remarkably, the improvement is more significant when the learning capacity (e.g., model size) is limited, suggesting that MixCo might be more useful in real-world scenarios. The code is available at: https://github.com/Lee-Gihun/MixCo-Mixup-Contrast.