Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a great number of supervised learning-based enhancement and separation methods having been proposed and achieving good performance, studies on applying self-supervised learning (SSL) to enhancement and separation are limited. In this paper, we evaluate 13 SSL upstream methods on speech enhancement and separation downstream tasks. Our experimental results on Voicebank-DEMAND and Libri2Mix show that some SSL representations consistently outperform baseline features including the short-time Fourier transform (STFT) magnitude and log Mel filterbank (FBANK). Furthermore, we analyze the factors that make existing SSL frameworks difficult to apply to speech enhancement and separation and discuss the representation properties desired for both tasks. Our study is included as the official speech enhancement and separation downstreams for SUPERB.
In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods.
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image. We build our work upon the recent advances of DNN-based auto-encoders with differentiable ray tracing image formation, trained in self-supervised manner. While providing the advantage of learning-based approaches and real-time reconstruction, the latter methods lacked fidelity. In this work, we achieve, for the first time, high fidelity face reconstruction using self-supervised learning only. Our novel coarse-to-fine deep architecture allows us to solve the challenging problem of decoupling face reflectance from geometry using a single image, at high computational speed. Compared to state-of-the-art methods, our method achieves more visually appealing reconstruction.
This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors. Other state-of-theart works mainly focus on fully supervised learning approaches that rely heavily on human annotations. However, the scarcity of labeled and unlabeled data is a long-standing challenge in histopathology. Currently, representation learning without labels remains unexplored for the histopathology domain. The proposed method, Magnification Prior Contrastive Similarity (MPCS), enables self-supervised learning of representations without labels on small-scale breast cancer dataset BreakHis by exploiting magnification factor, inductive transfer, and reducing human prior. The proposed method matches fully supervised learning state-of-the-art performance in malignancy classification when only 20% of labels are used in fine-tuning and outperform previous works in fully supervised learning settings. It formulates a hypothesis and provides empirical evidence to support that reducing human-prior leads to efficient representation learning in self-supervision. The implementation of this work is available online on GitHub - https://github.com/prakashchhipa/Magnification-Prior-Self-Supervised-Method
Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly focuses on contrastive learning in single instance, it ignores the objective differences between pretext and downstream prediction tasks such as object detection and instance segmentation. In order to fully unleash the power of feature representation on downstream prediction tasks, we propose a new end-to-end self-supervised framework called InsCon, which is devoted to capturing multi-instance information and extracting cell-instance features for object recognition and localization. On the one hand, InsCon builds a targeted learning paradigm that applies multi-instance images as input, aligning the learned feature between corresponding instance views, which makes it more appropriate for multi-instance recognition tasks. On the other hand, InsCon introduces the pull and push of cell-instance, which utilizes cell consistency to enhance fine-grained feature representation for precise boundary localization. As a result, InsCon learns multi-instance consistency on semantic feature representation and cell-instance consistency on spatial feature representation. Experiments demonstrate the method we proposed surpasses MoCo v2 by 1.1% AP^{bb} on COCO object detection and 1.0% AP^{mk} on COCO instance segmentation using Mask R-CNN R50-FPN network structure with 90k iterations, 2.1% APbb on PASCAL VOC objection detection using Faster R-CNN R50-C4 network structure with 24k iterations.
Previous few-shot learning (FSL) works mostly are limited to natural images of general concepts and categories. These works assume very high visual similarity between the source and target classes. In contrast, the recently proposed cross-domain few-shot learning (CD-FSL) aims at transferring knowledge from general nature images of many labeled examples to novel domain-specific target categories of only a few labeled examples. The key challenge of CD-FSL lies in the huge data shift between source and target domains, which is typically in the form of totally different visual styles. This makes it very nontrivial to directly extend the classical FSL methods to address the CD-FSL task. To this end, this paper studies the problem of CD-FSL by spanning the style distributions of the source dataset. Particularly, wavelet transform is introduced to enable the decomposition of visual representations into low-frequency components such as shape and style and high-frequency components e.g., texture. To make our model robust to visual styles, the source images are augmented by swapping the styles of their low-frequency components with each other. We propose a novel Style Augmentation (StyleAug) module to implement this idea. Furthermore, we present a Self-Supervised Learning (SSL) module to ensure the predictions of style-augmented images are semantically similar to the unchanged ones. This avoids the potential semantic drift problem in exchanging the styles. Extensive experiments on two CD-FSL benchmarks show the effectiveness of our method. Our codes and models will be released.
It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies an image with a worst-case but humanly imperceptible perturbation (so-called adversarial examples). To tackle this problem, a great amount of research has been done to study the training procedure of a network to improve its robustness. However, most of the research so far has focused on the case of supervised learning. With the increasing popularity of self-supervised learning methods, it is also important to study and improve the robustness of their resulting representation on the downstream tasks. In this paper, we study the problem of robust representation learning with unlabeled data in a task-agnostic manner. Specifically, we first derive an upper bound on the adversarial loss of a prediction model (which is based on the learned representation) on any downstream task, using its loss on the clean data and a robustness regularizer. Moreover, the regularizer is task-independent, thus we propose to minimize it directly during the representation learning phase to make the downstream prediction model more robust. Extensive experiments show that our method achieves preferable adversarial performance compared to relevant baselines.
The current literature on self-supervised learning (SSL) focuses on developing learning objectives to train neural networks more effectively on unlabeled data. The typical development process involves taking well-established architectures, e.g., ResNet demonstrated on ImageNet, and using them to evaluate newly developed objectives on downstream scenarios. While convenient, this does not take into account the role of architectures which has been shown to be crucial in the supervised learning literature. In this work, we establish extensive empirical evidence showing that a network architecture plays a significant role in SSL. We conduct a large-scale study with over 100 variants of ResNet and MobileNet architectures and evaluate them across 11 downstream scenarios in the SSL setting. We show that there is no one network that performs consistently well across the scenarios. Based on this, we propose to learn not only network weights but also architecture topologies in the SSL regime. We show that "self-supervised architectures" outperform popular handcrafted architectures (ResNet18 and MobileNetV2) while performing competitively with the larger and computationally heavy ResNet50 on major image classification benchmarks (ImageNet-1K, iNat2021, and more). Our results suggest that it is time to consider moving beyond handcrafted architectures in SSL and start thinking about incorporating architecture search into self-supervised learning objectives.
Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.
In recent years, self-supervised learning methods have shown significant improvement for pre-training with unlabeled data and have proven helpful for electrocardiogram signals. However, most previous pre-training methods for electrocardiogram focused on capturing only global contextual representations. This inhibits the models from learning fruitful representation of electrocardiogram, which results in poor performance on downstream tasks. Additionally, they cannot fine-tune the model with an arbitrary set of electrocardiogram leads unless the models were pre-trained on the same set of leads. In this work, we propose an ECG pre-training method that learns both local and global contextual representations for better generalizability and performance on downstream tasks. In addition, we propose random lead masking as an ECG-specific augmentation method to make our proposed model robust to an arbitrary set of leads. Experimental results on two downstream tasks, cardiac arrhythmia classification and patient identification, show that our proposed approach outperforms other state-of-the-art methods.
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the scene and instances, as well as the semantic difference of instances in the scene. To address the above problems, we propose a Unified Self-supervised Visual Pre-training (UniVIP), a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. The framework takes into account the representation learning at three levels: 1) the similarity of scene-scene, 2) the correlation of scene-instance, 3) the discrimination of instance-instance. During the learning, we adopt the optimal transport algorithm to automatically measure the discrimination of instances. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance on a variety of downstream tasks, such as image classification, semi-supervised learning, object detection and segmentation. Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
Recent advancements in deep learning methods bring computer-assistance a step closer to fulfilling promises of safer surgical procedures. However, the generalizability of such methods is often dependent on training on diverse datasets from multiple medical institutions, which is a restrictive requirement considering the sensitive nature of medical data. Recently proposed collaborative learning methods such as Federated Learning (FL) allow for training on remote datasets without the need to explicitly share data. Even so, data annotation still represents a bottleneck, particularly in medicine and surgery where clinical expertise is often required. With these constraints in mind, we propose FedCy, a federated semi-supervised learning (FSSL) method that combines FL and self-supervised learning to exploit a decentralized dataset of both labeled and unlabeled videos, thereby improving performance on the task of surgical phase recognition. By leveraging temporal patterns in the labeled data, FedCy helps guide unsupervised training on unlabeled data towards learning task-specific features for phase recognition. We demonstrate significant performance gains over state-of-the-art FSSL methods on the task of automatic recognition of surgical phases using a newly collected multi-institutional dataset of laparoscopic cholecystectomy videos. Furthermore, we demonstrate that our approach also learns more generalizable features when tested on data from an unseen domain.
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric representations with self-supervision and validate our insights through several experiments on the CLEVR dataset. Regarding the architecture, we confirm the importance of competition for attention-based object discovery, where each image patch is exclusively attended by one object. For training, we show that contrastive losses equipped with matching can be applied directly in a latent space, avoiding pixel-based reconstruction. However, such an optimization objective is sensitive to false negatives (recurring objects) and false positives (matching errors). Careful consideration is thus required around data augmentation and negative sample selection.
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our network to predict high-quality depths. We demonstrate that our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments. Our full system shows improvements over recent self-supervised depth estimation and completion methods on EuRoC, OpenLORIS, and ScanNet datasets.
Cereal grains are a vital part of human diets and are important commodities for people's livelihood and international trade. Grain Appearance Inspection (GAI) serves as one of the crucial steps for the determination of grain quality and grain stratification for proper circulation, storage and food processing, etc. GAI is routinely performed manually by qualified inspectors with the aid of some hand tools. Automated GAI has the benefit of greatly assisting inspectors with their jobs but has been limited due to the lack of datasets and clear definitions of the tasks. In this paper we formulate GAI as three ubiquitous computer vision tasks: fine-grained recognition, domain adaptation and out-of-distribution recognition. We present a large-scale and publicly available cereal grains dataset called GrainSpace. Specifically, we construct three types of device prototypes for data acquisition, and a total of 5.25 million images determined by professional inspectors. The grain samples including wheat, maize and rice are collected from five countries and more than 30 regions. We also develop a comprehensive benchmark based on semi-supervised learning and self-supervised learning techniques. To the best of our knowledge, GrainSpace is the first publicly released dataset for cereal grain inspection.
Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhance label efficiency. However, this approach faces a bottleneck in reducing the need for labels. We observed that the semi-supervised model disrupts valuable information from self-supervised learning when only limited labels are available. To address this issue, this paper proposes a simple yet effective framework, active self-semi-supervised learning (AS3L). AS3L bootstraps semi-supervised models with prior pseudo-labels (PPL). These PPLs are obtained by label propagation over self-supervised features. Based on the observations the accuracy of PPL is not only affected by the quality of features but also by the selection of the labeled samples. We develop active learning and label propagation strategies to obtain accurate PPL. Consequently, our framework can significantly improve the performance of models in the case of limited annotations while demonstrating fast convergence. On the image classification tasks across four datasets, our method outperforms the baseline by an average of 5.4\%. Additionally, it achieves the same accuracy as the baseline method in about 1/3 of the training time.
A large-scale labeled dataset is a key factor for the success of supervised deep learning in computer vision. However, a limited number of annotated data is very common, especially in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not need massive annotations. With an attempt to use as many as possible unlabeled ophthalmic images, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images. In this paper, we propose a universal self-supervised Transformer framework, named Uni4Eye, to discover the inherent image property and capture domain-specific feature embedding in ophthalmic images. Uni4Eye can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer (ViT) architecture. We employ a Unified Patch Embedding module to replace the origin patch embedding module in ViT for jointly processing both 2D and 3D input images. Besides, we design a dual-branch multitask decoder module to simultaneously perform two reconstruction tasks on the input image and its gradient map, delivering discriminative representations for better convergence. We evaluate the performance of our pre-trained Uni4Eye encoder by fine-tuning it on six downstream ophthalmic image classification tasks. The superiority of Uni4Eye is successfully established through comparisons to other state-of-the-art SSL pre-training methods.
In this paper, we study the cluster head detection problem of a two-level unmanned aerial vehicle (UAV) swarm network (USNET) with multiple UAV clusters, where the inherent follow strategy (IFS) of low-level follower UAVs (FUAVs) with respect to high-level cluster head UAVs (HUAVs) is unknown. We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time. Then, to detect the HUAVs in the USNET with multiple UAV clusters, we develop a multi-cluster graph attention self-supervised learning algorithm (MC-GASSL) based on the GASSL. The MC-GASSL clusters the USNET with a gated recurrent unit (GRU)-based metric learning scheme and finds the HUAVs in each cluster with GASSL. Numerical results show that the GASSL can detect the HUAVs in single UAV clusters obeying various kinds of IFSs with over 98% average accuracy. The simulation results also show that the clustering purity of the USNET with MC-GASSL exceeds that with traditional clustering algorithms by at least 10% average. Furthermore, the MC-GASSL can efficiently detect all the HUAVs in USNETs with various IFSs and cluster numbers with low detection redundancies.
Self-supervised representation learning of Multivariate Time Series (MTS) is a challenging task and attracts increasing research interests in recent years. Many previous works focus on the pretext task of self-supervised learning and usually neglect the complex problem of MTS encoding, leading to unpromising results. In this paper, we tackle this challenge from two aspects: encoder and pretext task, and propose a unified channel-aware self-supervised learning framework CaSS. Specifically, we first design a new Transformer-based encoder Channel-aware Transformer (CaT) to capture the complex relationships between different time channels of MTS. Second, we combine two novel pretext tasks Next Trend Prediction (NTP) and Contextual Similarity (CS) for the self-supervised representation learning with our proposed encoder. Extensive experiments are conducted on several commonly used benchmark datasets. The experimental results show that our framework achieves new state-of-the-art comparing with previous self-supervised MTS representation learning methods (up to +7.70\% improvement on LSST dataset) and can be well applied to the downstream MTS classification.
In this work, we propose two novel methodologies to study temporal and morphological phenotypic effects caused by different experimental conditions using imaging data. As a proof of concept, we apply them to analyze drug effects in 2D cancer cell cultures. We train a convolutional autoencoder on 1M images dataset with random augmentations and multi-crops to use as feature extractor. We systematically compare it to the pretrained state-of-the-art models. We further use the feature extractor in two ways. First, we apply distance-based analysis and dynamic time warping to cluster temporal patterns of 31 drugs. We identify clusters allowing annotation of drugs as having cytotoxic, cytostatic, mixed or no effect. Second, we implement an adversarial/regularized learning setup to improve classification of 31 drugs and visualize image regions that contribute to the improvement. We increase top-3 classification accuracy by 8% on average and mine examples of morphological feature importance maps. We provide the feature extractor and the weights to foster transfer learning applications in biology. We also discuss utility of other pretrained models and applicability of our methods to other types of biomedical data.