Recently, the amount of GI tract datasets is introduced more and more by gathering from contests and challenges. The most common task needs to solve that is to classify images from the GI tract into various classes. However, the contributions of the existing approaches exhibit lots of limitations. In this paper, we aim to develop a computer-aided diagnosis system to classify the pathological findings in endoscopy images, the system can classify some common pathologies including polyps, esophagitis, and ulcerative -- colitis. To evaluate the proposed work, we use the public dataset which is Hyper--Kvasir instead of gathering the data. The key idea of our system is to develop self-supervised learning based on the Barlow Twins framework with a downstream task which is an endoscopy image classification integrated with triplet loss and focal loss functions. The self-supervision framework and focal loss function are used to overcome class-imbalanced data, while the triplet loss function is to tackle the domain-specific properties in endoscopy images which are inter/intra-class problems. An extensive experimental study on the pathological finding images in the Hyper--Kvasir dataset has shown that our proposed system is in general better than the compared methods, whereas using a simple neural network model. This means the proposed system can be used efficiently and capable of accurately for the classification of pathology images in the GI tract.
Sequential recommendations aim to capture users' preferences from their historical interactions so as to predict the next item that they will interact with. Sequential recommendation methods usually assume that all items in a user's historical interactions reflect her/his preferences and transition patterns between items. However, real-world interaction data is imperfect in that (i) users might erroneously click on items, i.e., so-called misclicks on irrelevant items, and (ii) users might miss items, i.e., unexposed relevant items due to inaccurate recommendations. To tackle the two issues listed above, we propose STEAM, a Self-correcTing sEquentiAl recoMmender. STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items. It then uses the corrected item sequence to train a recommender and make the next item prediction.We design an item-wise corrector that can adaptively select one type of operation for each item in the sequence. The operation types are 'keep', 'delete' and 'insert.' In order to train the item-wise corrector without requiring additional labeling, we design two self-supervised learning mechanisms: (i) deletion correction (i.e., deleting randomly inserted items), and (ii) insertion correction (i.e., predicting randomly deleted items). We integrate the corrector with the recommender by sharing the encoder and by training them jointly. We conduct extensive experiments on three real-world datasets and the experimental results demonstrate that STEAM outperforms state-of-the-art sequential recommendation baselines. Our in-depth analyses confirm that STEAM benefits from learning to correct the raw item sequences.
Recent work has explored using self-supervised learning (SSL) speech representations such as wav2vec2.0 as the representation medium in standard two-stage TTS, in place of conventionally used mel-spectrograms. It is however unclear which speech SSL is the better fit for TTS, and whether or not the performance differs between read and spontaneous TTS, the later of which is arguably more challenging. This study aims at addressing these questions by testing several speech SSLs, including different layers of the same SSL, in two-stage TTS on both read and spontaneous corpora, while maintaining constant TTS model architecture and training settings. Results from listening tests show that the 9th layer of 12-layer wav2vec2.0 (ASR finetuned) outperforms other tested SSLs and mel-spectrogram, in both read and spontaneous TTS. Our work sheds light on both how speech SSL can readily improve current TTS systems, and how SSLs compare in the challenging generative task of TTS. Audio examples can be found at https://www.speech.kth.se/tts-demos/ssr_tts
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, {\ourmethod}, that entails two strategies: 1) filtering the high-frequency components from the reconstruction target to de-emphasize the network's focus on texture-rich details and 2) adopting a conservative data transform strategy to alleviate the problem of missing foreground in MIM training. {\ourmethod} can be easily integrated into most existing pixel-based MIM approaches (\ie, using raw images as reconstruction target) with negligible additional computation. Without bells and whistles, our method consistently improves three MIM approaches, MAE, ConvMAE, and LSMAE, across various downstream tasks. We believe this effective plug-and-play method will serve as a strong baseline for self-supervised learning and provide insights for future improvements of the MIM framework. Code and models are available at \url{https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/pixmim}.
Visual place recognition is a key to unlocking spatial navigation for animals, humans and robots. While state-of-the-art approaches are trained in a supervised manner and therefore hardly capture the information needed for generalizing to unusual conditions, we argue that self-supervised learning may help abstracting the place representation so that it can be foreseen, irrespective of the conditions. More precisely, in this paper, we investigate learning features that are robust to appearance modifications while sensitive to geometric transformations in a self-supervised manner. This dual-purpose training is made possible by combining the two self-supervision main paradigms, \textit{i.e.} contrastive and predictive learning. Our results on standard benchmarks reveal that jointly learning such appearance-robust and geometry-sensitive image descriptors leads to competitive visual place recognition results across adverse seasonal and illumination conditions, without requiring any human-annotated labels.
The success of self-supervised learning (SSL) has mostly been attributed to the availability of unlabeled yet large-scale datasets. However, in a specialized domain such as medical imaging which is a lot different from natural images, the assumption of data availability is unrealistic and impractical, as the data itself is scanty and found in small databases, collected for specific prognosis tasks. To this end, we seek to investigate the applicability of self-supervised learning algorithms on small-scale medical imaging datasets. In particular, we evaluate $4$ state-of-the-art SSL methods on three publicly accessible \emph{small} medical imaging datasets. Our investigation reveals that in-domain low-resource SSL pre-training can yield competitive performance to transfer learning from large-scale datasets (such as ImageNet). Furthermore, we extensively analyse our empirical findings to provide valuable insights that can motivate for further research towards circumventing the need for pre-training on a large image corpus. To the best of our knowledge, this is the first attempt to holistically explore self-supervision on low-resource medical datasets.
The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs such that they capture maximal information about the environment, subject to biological constraints. While elegant, information theoretic properties are notoriously difficult to measure in practical settings or to employ as objective functions in optimization. This difficulty has necessitated that computational models designed to test the hypothesis employ several different information metrics ranging from approximations and lower bounds to proxy measures like reconstruction error. Recent theoretical advances have characterized a novel and ecologically relevant efficiency metric, the manifold capacity, which is the number of object categories that may be represented in a linearly separable fashion. However, calculating manifold capacity is a computationally intensive iterative procedure that until now has precluded its use as an objective. Here we outline the simplifying assumptions that allow manifold capacity to be optimized directly, yielding Maximum Manifold Capacity Representations (MMCR). The resulting method is closely related to and inspired by advances in the field of self supervised learning (SSL), and we demonstrate that MMCRs are competitive with state of the art results on standard SSL benchmarks. Empirical analyses reveal differences between MMCRs and representations learned by other SSL frameworks, and suggest a mechanism by which manifold compression gives rise to class separability. Finally we evaluate a set of SSL methods on a suite of neural predictivity benchmarks, and find MMCRs are higly competitive as models of the ventral stream.
Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated training data. However, in the case of historical manuscripts, there is a lack of annotated corpus for training. To handle the data scarcity issue, we investigate the merits of the self-supervised learning to extract useful representations of the input data without relying on human annotations and then using these representations in the downstream task. We propose ST-KeyS, a masked auto-encoder model based on vision transformers where the pretraining stage is based on the mask-and-predict paradigm, without the need of labeled data. In the fine-tuning stage, the pre-trained encoder is integrated into a siamese neural network model that is fine-tuned to improve feature embedding from the input images. We further improve the image representation using pyramidal histogram of characters (PHOC) embedding to create and exploit an intermediate representation of images based on text attributes. In an exhaustive experimental evaluation on three widely used benchmark datasets (Botany, Alvermann Konzilsprotokolle and George Washington), the proposed approach outperforms state-of-the-art methods trained on the same datasets.
Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage large unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever increasing downstream classification accuracies, using huge computational resources, and typically built upon insights and intuitions inherited from a close parent JE-SSL method. This has led unwittingly to numerous pre-conceived ideas that carried over across methods e.g. that SimCLR requires very large mini batches to yield competitive accuracies; that strong and computationally slow data augmentations are required. In this work, we debunk several such ill-formed a priori ideas in the hope to unleash the full potential of JE-SSL free of unnecessary limitations. In fact, when carefully evaluating performances across different downstream tasks and properly optimizing hyper-parameters of the methods, we most often -- if not always -- see that these widespread misconceptions do not hold. For example we show that it is possible to train SimCLR to learn useful representations, while using a single image patch as negative example, and simple Gaussian noise as the only data augmentation for the positive pair. Along these lines, in the hope to democratize JE-SSL and to allow researchers to easily make more extensive evaluations of their methods, we introduce an optimized PyTorch library for SSL.
A large body of previous machine learning methods for ultrasound-based prostate cancer detection classify small regions of interest (ROIs) of ultrasound signals that lie within a larger needle trace corresponding to a prostate tissue biopsy (called biopsy core). These ROI-scale models suffer from weak labeling as histopathology results available for biopsy cores only approximate the distribution of cancer in the ROIs. ROI-scale models do not take advantage of contextual information that are normally considered by pathologists, i.e. they do not consider information about surrounding tissue and larger-scale trends when identifying cancer. We aim to improve cancer detection by taking a multi-scale, i.e. ROI-scale and biopsy core-scale, approach. Methods: Our multi-scale approach combines (i) an "ROI-scale" model trained using self-supervised learning to extract features from small ROIs and (ii) a "core-scale" transformer model that processes a collection of extracted features from multiple ROIs in the needle trace region to predict the tissue type of the corresponding core. Attention maps, as a byproduct, allow us to localize cancer at the ROI scale. We analyze this method using a dataset of micro-ultrasound acquired from 578 patients who underwent prostate biopsy, and compare our model to baseline models and other large-scale studies in the literature. Results and Conclusions: Our model shows consistent and substantial performance improvements compared to ROI-scale-only models. It achieves 80.3% AUROC, a statistically significant improvement over ROI-scale classification. We also compare our method to large studies on prostate cancer detection, using other imaging modalities. Our code is publicly available at www.github.com/med-i-lab/TRUSFormer
Single-Photon Image Super-Resolution (SPISR) aims to recover a high-resolution volumetric photon counting cube from a noisy low-resolution one by computational imaging algorithms. In real-world scenarios, pairs of training samples are often expensive or impossible to obtain. By extending Equivariant Imaging (EI) to volumetric single-photon data, we propose a self-supervised learning framework for the SPISR task. Particularly, using the Poisson unbiased Kullback-Leibler risk estimator and equivariance, our method is able to learn from noisy measurements without ground truths. Comprehensive experiments on simulated and real-world dataset demonstrate that the proposed method achieves comparable performance with supervised learning and outperforms interpolation-based methods.
Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic point cloud completion task, it is hardly applicable in real-world scenarios due to the domain gap between the synthetic and real-world datasets or the requirement of prior information. To overcome these limitations, we propose a novel self-supervised framework ACL-SPC for point cloud completion to train and test on the same data. ACL-SPC takes a single partial input and attempts to output the complete point cloud using an adaptive closed-loop (ACL) system that enforces the output same for the variation of an input. We evaluate our proposed ACL-SPC on various datasets to prove that it can successfully learn to complete a partial point cloud as the first self-supervised scheme. Results show that our method is comparable with unsupervised methods and achieves superior performance on the real-world dataset compared to the supervised methods trained on the synthetic dataset. Extensive experiments justify the necessity of self-supervised learning and the effectiveness of our proposed method for the real-world point cloud completion task. The code is publicly available from https://github.com/Sangminhong/ACL-SPC_PyTorch
Self-supervised learning (SSL) strategies have demonstrated remarkable performance in various recognition tasks. However, both our preliminary investigation and recent studies suggest that they may be less effective in learning representations for fine-grained visual recognition (FGVR) since many features helpful for optimizing SSL objectives are not suitable for characterizing the subtle differences in FGVR. To overcome this issue, we propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes, dubbed as common rationales in this paper. Intuitively, common rationales tend to correspond to the discriminative patterns from the key parts of foreground objects. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective without using any pre-trained object parts or saliency detectors, making it seamlessly to be integrated with the existing SSL process. Specifically, we fit the GradCAM with a branch with limited fitting capacity, which allows the branch to capture the common rationales and discard the less common discriminative patterns. At the test stage, the branch generates a set of spatial weights to selectively aggregate features representing an instance. Extensive experimental results on four visual tasks demonstrate that the proposed method can lead to a significant improvement in different evaluation settings.
Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learning technique is based on an auxiliary stage aka pretext task in which labeled data are created automatically through data augmentation and exploited for pretraining the DNN. However, the effect of each pretext task is not well studied or compared in the literature. In this paper, we study the contribution of augmentation operators on the performance of self supervised learning algorithms in a constrained settings. We propose an evolutionary search method for optimization of data augmentation pipeline in pretext tasks and measure the impact of augmentation operators in several SOTA SSL algorithms. By encoding different combination of augmentation operators in chromosomes we seek the optimal augmentation policies through an evolutionary optimization mechanism. We further introduce methods for analyzing and explaining the performance of optimized SSL algorithms. Our results indicate that our proposed method can find solutions that outperform the accuracy of classification of SSL algorithms which confirms the influence of augmentation policy choice on the overall performance of SSL algorithms. We also compare optimal SSL solutions found by our evolutionary search mechanism and show the effect of batch size in the pretext task on two visual datasets.
Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (self-AT) remains significant. Motivated by this observation, we revisit existing self-AT methods and discover an inherent dilemma that affects self-AT robustness: either strong or weak data augmentations are harmful to self-AT, and a medium strength is insufficient to bridge the gap. To resolve this dilemma, we propose a simple remedy named DYNACL (Dynamic Adversarial Contrastive Learning). In particular, we propose an augmentation schedule that gradually anneals from a strong augmentation to a weak one to benefit from both extreme cases. Besides, we adopt a fast post-processing stage for adapting it to downstream tasks. Through extensive experiments, we show that DYNACL can improve state-of-the-art self-AT robustness by 8.84% under Auto-Attack on the CIFAR-10 dataset, and can even outperform vanilla supervised adversarial training for the first time. Our code is available at \url{https://github.com/PKU-ML/DYNACL}.
We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to a new language in low resource setup and generalizes to languages not seen while training the self-supervised backbone. Moreover, without training on bilingual or parallel examples, ParrotTTS can transfer voices across languages while preserving the speaker specific characteristics, e.g., synthesizing fluent Hindi speech using a French speaker's voice and accent. We present extensive results in monolingual and multi-lingual scenarios. ParrotTTS outperforms state-of-the-art multi-lingual TTS models using only a fraction of paired data as latter.
Graph Neural Networks (GNNs) have become powerful tools in modeling graph-structured data in recommender systems. However, real-life recommendation scenarios usually involve heterogeneous relationships (e.g., social-aware user influence, knowledge-aware item dependency) which contains fruitful information to enhance the user preference learning. In this paper, we study the problem of heterogeneous graph-enhanced relational learning for recommendation. Recently, contrastive self-supervised learning has become successful in recommendation. In light of this, we propose a Heterogeneous Graph Contrastive Learning (HGCL), which is able to incorporate heterogeneous relational semantics into the user-item interaction modeling with contrastive learning-enhanced knowledge transfer across different views. However, the influence of heterogeneous side information on interactions may vary by users and items. To move this idea forward, we enhance our heterogeneous graph contrastive learning with meta networks to allow the personalized knowledge transformer with adaptive contrastive augmentation. The experimental results on three real-world datasets demonstrate the superiority of HGCL over state-of-the-art recommendation methods. Through ablation study, key components in HGCL method are validated to benefit the recommendation performance improvement. The source code of the model implementation is available at the link https://github.com/HKUDS/HGCL.
Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training distributions differ. However, the theoretical understanding of its transferability remains limited. In this paper, we develop a theoretical framework to analyze the transferability of self-supervised contrastive learning, by investigating the impact of data augmentation on it. Our results reveal that the downstream performance of contrastive learning depends largely on the choice of data augmentation. Moreover, we show that contrastive learning fails to learn domain-invariant features, which limits its transferability. Based on these theoretical insights, we propose a novel method called Augmentation-robust Contrastive Learning (ArCL), which guarantees to learn domain-invariant features and can be easily integrated with existing contrastive learning algorithms. We conduct experiments on several datasets and show that ArCL significantly improves the transferability of contrastive learning.
Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label information; recent works have proposed to create, e.g., pseudo-labeling via pretrained representations or creating synthetic samples via generative models. However, such a task construction strategy is fundamentally limited due to heavy reliance on the immutable pseudo-labels during meta-learning and the quality of the representations or the generated samples. To overcome the limitations, we propose a simple yet effective unsupervised meta-learning framework, coined Pseudo-supervised Contrast (PsCo), for few-shot classification. We are inspired by the recent self-supervised learning literature; PsCo utilizes a momentum network and a queue of previous batches to improve pseudo-labeling and construct diverse tasks in a progressive manner. Our extensive experiments demonstrate that PsCo outperforms existing unsupervised meta-learning methods under various in-domain and cross-domain few-shot classification benchmarks. We also validate that PsCo is easily scalable to a large-scale benchmark, while recent prior-art meta-schemes are not.
Blind image quality assessment (BIQA) aims to automatically evaluate the perceived quality of a single image, whose performance has been improved by deep learning-based methods in recent years. However, the paucity of labeled data somewhat restrains deep learning-based BIQA methods from unleashing their full potential. In this paper, we propose to solve the problem by a pretext task customized for BIQA in a self-supervised learning manner, which enables learning representations from orders of magnitude more data. To constrain the learning process, we propose a quality-aware contrastive loss based on a simple assumption: the quality of patches from a distorted image should be similar, but vary from patches from the same image with different degradations and patches from different images. Further, we improve the existing degradation process and form a degradation space with the size of roughly $2\times10^7$. After pre-trained on ImageNet using our method, models are more sensitive to image quality and perform significantly better on downstream BIQA tasks. Experimental results show that our method obtains remarkable improvements on popular BIQA datasets.