The main objective is to provide several solutions to the mentioned problems, by focusing on analyzing previous state-of-the-art methods and presenting an extensive overview to clarify the concepts employed on capturing normal and abnormal patterns. Also, by exploring different strategies, we were able to develop new approaches that consistently advance the state-of-the-art performance. Moreover, we announce the availability of a new large-scale first of its kind dataset fully annotated at the frame level, concerning a specific anomaly detection event with a wide diversity in fighting scenarios, that can be freely used by the research community. Along with this document with the purpose of requiring minimal supervision, two different proposals are described; the first method employs the recent technique of self-supervised learning to avoid the laborious task of annotation, where the training set is autonomously labeled using an iterative learning framework composed of two independent experts that feed data to each other through a Bayesian framework. The second proposal explores a new method to learn an anomaly ranking model in the multiple instance learning paradigm by leveraging weakly labeled videos, where the training labels are done at the video-level. The experiments were conducted in several well-known datasets, and our solutions solidly outperform the state-of-the-art. Additionally, as a proof-of-concept system, we also present the results of collected real-world simulations in different environments to perform a field test of our learned models.
This paper presents Contrastive Reconstruction, ConRec - a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss. We showcase that state-of-the-art contrastive learning methods (e.g. SimCLR) have shortcomings to capture fine-grained visual features in their representations. ConRec extends the SimCLR framework by adding (1) a self-reconstruction task and (2) an attention mechanism within the contrastive learning task. This is accomplished by applying a simple encoder-decoder architecture with two heads. We show that both extensions contribute towards an improved vector representation for images with fine-grained visual features. Combining those concepts, ConRec outperforms SimCLR and SimCLR with Attention-Pooling on fine-grained classification datasets.
This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream tasks of visual correspondence, object tracking, and object detection. The model infers a latent3D representation of the scene in the form of 3D feature points, where each continuous world 3D point is mapped to its corresponding feature vector. The model is trained for contrastive view prediction by rendering 3D feature clouds in queried viewpoints and matching against the 3D feature point cloud predicted from the query view. Notably, the representation can be queried for any 3D location, even if it is not visible from the input view. Our model brings together three powerful ideas of recent exciting research work: 3D feature grids as a neural bottleneck for view prediction, implicit functions for handling resolution limitations of 3D grids, and contrastive learning for unsupervised training of feature representations. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection. We outperform many existing state-of-the-art methods for 3D feature learning and view prediction, which are either limited by 3D grid spatial resolution, do not attempt to build amodal 3D representations, or do not handle combinatorial scene variability due to their non-convolutional bottlenecks.
This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples. Conventional wisdom dictates that in order to achieve good speech denoising performance, there is a requirement for a large quantity of both noisy speech samples and perfectly clean speech samples, resulting in a need for expensive audio recording equipment and extremely controlled soundproof recording studios. These requirements pose significant challenges in data collection, especially in economically disadvantaged regions and for low resource languages. This work shows that speech denoising deep neural networks can be successfully trained utilizing only noisy training audio. Furthermore it is revealed that such training regimes achieve superior denoising performance over conventional training regimes utilizing clean training audio targets, in cases involving complex noise distributions and low Signal-to-Noise ratios (high noise environments). This is demonstrated through experiments studying the efficacy of our proposed approach over both real-world noises and synthetic noises using the 20 layered Deep Complex U-Net architecture.
Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are already the methods of choice. The recent literature suggests that the transformers are becoming increasingly popular also in computer vision. So far, the vision transformers have been shown to work well when pretrained either using a large scale supervised data or with some kind of co-supervision, e.g. in terms of teacher network. These supervised pretrained vision transformers achieve very good results in downstream tasks with minimal changes. In this work we investigate the merits of self-supervised learning for pretraining image/vision transformers and then using them for downstream classification tasks. We propose Self-supervised vIsion Transformers (SiT) and discuss several self-supervised training mechanisms to obtain a pretext model. The architectural flexibility of SiT allows us to use it as an autoencoder and work with multiple self-supervised tasks seamlessly. We show that a pretrained SiT can be finetuned for a downstream classification task on small scale datasets, consisting of a few thousand images rather than several millions. The proposed approach is evaluated on standard datasets using common protocols. The results demonstrate the strength of the transformers and their suitability for self-supervised learning. We outperformed existing self-supervised learning methods by large margin. We also observed that SiT is good for few shot learning and also showed that it is learning useful representation by simply training a linear classifier on top of the learned features from SiT. Pretraining, finetuning, and evaluation codes will be available under: https://github.com/Sara-Ahmed/SiT.
Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the convolutional network structure itself, the long-range dependencies in both the spatial and temporal cannot be obtained efficiently. To incorporate the spatial layout, we propose to exploit the local correlation module to model the topological relationship between targets and their surrounding environment, which can enhance the discriminative power of our model in crowded scenes. Specifically, we establish dense correspondences of each spatial location and its context, and explicitly constrain the correlation volumes through self-supervised learning. To exploit the temporal context, existing approaches generally utilize two or more adjacent frames to construct an enhanced feature representation, but the dynamic motion scene is inherently difficult to depict via CNNs. Instead, our paper proposes a learnable correlation operator to establish frame-to-frame matches over convolutional feature maps in the different layers to align and propagate temporal context. With extensive experimental results on the MOT datasets, our approach demonstrates the effectiveness of correlation learning with the superior performance and obtains state-of-the-art MOTA of 76.5% and IDF1 of 73.6% on MOT17.
Any-to-any voice conversion (VC) aims to convert the timbre of utterances from and to any speakers seen or unseen during training. Various any-to-any VC approaches have been proposed like AUTOVC, AdaINVC, and FragmentVC. AUTOVC, and AdaINVC utilize source and target encoders to disentangle the content and speaker information of the features. FragmentVC utilizes two encoders to encode source and target information and adopts cross attention to align the source and target features with similar phonetic content. Moreover, pre-trained features are adopted. AUTOVC used dvector to extract speaker information, and self-supervised learning (SSL) features like wav2vec 2.0 is used in FragmentVC to extract the phonetic content information. Different from previous works, we proposed S2VC that utilizes Self-Supervised features as both source and target features for VC model. Supervised phoneme posteriororgram (PPG), which is believed to be speaker-independent and widely used in VC to extract content information, is chosen as a strong baseline for SSL features. The objective evaluation and subjective evaluation both show models taking SSL feature CPC as both source and target features outperforms that taking PPG as source feature, suggesting that SSL features have great potential in improving VC.
Algorithms learn rules and associations based on the training data that they are exposed to. Yet, the very same data that teaches machines to understand and predict the world, contains societal and historic biases, resulting in biased algorithms with the risk of further amplifying these once put into use for decision support. Synthetic data, on the other hand, emerges with the promise to provide an unlimited amount of representative, realistic training samples, that can be shared further without disclosing the privacy of individual subjects. We present a framework to incorporate fairness constraints into the self-supervised learning process, that allows to then simulate an unlimited amount of representative as well as fair synthetic data. This framework provides a handle to govern and control for privacy as well as for bias within AI at its very source: the training data. We demonstrate the proposed approach by amending an existing generative model architecture and generating a representative as well as fair version of the UCI Adult census data set. While the relationships between attributes are faithfully retained, the gender and racial biases inherent in the original data are controlled for. This is further validated by comparing propensity scores of downstream predictive models that are trained on the original data versus the fair synthetic data. We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
Recent supervised multi-view depth estimation networks have achieved promising results. Similar to all supervised approaches, these networks require ground-truth data during training. However, collecting a large amount of multi-view depth data is very challenging. Here, we propose a self-supervised learning framework for multi-view stereo that exploit pseudo labels from the input data. We start by learning to estimate depth maps as initial pseudo labels under an unsupervised learning framework relying on image reconstruction loss as supervision. We then refine the initial pseudo labels using a carefully designed pipeline leveraging depth information inferred from higher resolution images and neighboring views. We use these high-quality pseudo labels as the supervision signal to train the network and improve, iteratively, its performance by self-training. Extensive experiments on the DTU dataset show that our proposed self-supervised learning framework outperforms existing unsupervised multi-view stereo networks by a large margin and performs on par compared to the supervised counterpart. Code is available at https://github.com/JiayuYANG/Self-supervised-CVP-MVSNet.
Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature shift and temporal feature flip, in the mean teacher framework. The self-supervised branch defines two pretext tasks, including masked feature reconstruction and clip-order prediction, to learn the relation of temporal clues. By this means, SSTAP can better explore unlabeled videos, and improve the discriminative abilities of learned action features. We extensively evaluate the proposed SSTAP on THUMOS14 and ActivityNet v1.3 datasets. The experimental results demonstrate that SSTAP significantly outperforms state-of-the-art semi-supervised methods and even matches fully-supervised methods. Code is available at https://github.com/wangxiang1230/SSTAP.
Purpose: Manual annotation of gastric X-ray images by doctors for gastritis detection is time-consuming and expensive. To solve this, a self-supervised learning method is developed in this study. The effectiveness of the proposed self-supervised learning method in gastritis detection is verified using a few annotated gastric X-ray images. Methods: In this study, we develop a novel method that can perform explicit self-supervised learning and learn discriminative representations from gastric X-ray images. Models trained based on the proposed method were fine-tuned on datasets comprising a few annotated gastric X-ray images. Five self-supervised learning methods, i.e., SimSiam, BYOL, PIRL-jigsaw, PIRL-rotation, and SimCLR, were compared with the proposed method. Furthermore, three previous methods, one pretrained on ImageNet, one trained from scratch, and one semi-supervised learning method, were compared with the proposed method. Results: The proposed method's harmonic mean score of sensitivity and specificity after fine-tuning with the annotated data of 10, 20, 30, and 40 patients were 0.875, 0.911, 0.915, and 0.931, respectively. The proposed method outperformed all comparative methods, including the five self-supervised learning and three previous methods. Experimental results showed the effectiveness of the proposed method in gastritis detection using a few annotated gastric X-ray images. Conclusions: This paper proposes a novel self-supervised learning method based on a teacher-student architecture for gastritis detection using gastric X-ray images. The proposed method can perform explicit self-supervised learning and learn discriminative representations from gastric X-ray images. The proposed method exhibits potential clinical use in gastritis detection using a few annotated gastric X-ray images.
Recently, Self-supervised learning methods able to perform image denoising without ground truth labels have been proposed. These methods create low-quality images by adding random or Gaussian noise to images and then train a model for denoising. Ideally, it would be beneficial if one can generate high-quality CT images with only a few training samples via self-supervision. However, the performance of CT denoising is generally limited due to the complexity of CT noise. To address this problem, we propose a novel self-supervised learning-based CT denoising method. In particular, we train pre-train CT denoising and noise models that can predict CT noise from Low-dose CT (LDCT) using available LDCT and Normal-dose CT (NDCT) pairs. For a given test LDCT, we generate Pseudo-LDCT and NDCT pairs using the pre-trained denoising and noise models and then update the parameters of the denoising model using these pairs to remove noise in the test LDCT. To make realistic Pseudo LDCT, we train multiple noise models from individual images and generate the noise using the ensemble of noise models. We evaluate our method on the 2016 AAPM Low-Dose CT Grand Challenge dataset. The proposed ensemble noise model can generate realistic CT noise, and thus our method significantly improves the denoising performance existing denoising models trained by supervised- and self-supervised learning.
This paper addresses unsupervised action segmentation. Prior work captures the frame-level temporal structure of videos by a feature embedding that encodes time locations of frames in the video. We advance prior work with a new self-supervised learning (SSL) of a feature embedding that accounts for both frame- and action-level structure of videos. Our SSL trains an RNN to recognize positive and negative action sequences, and the RNN's hidden layer is taken as our new action-level feature embedding. The positive and negative sequences consist of action segments sampled from videos, where in the former the sampled action segments respect their time ordering in the video, and in the latter they are shuffled. As supervision of actions is not available and our SSL requires access to action segments, we specify an HMM that explicitly models action lengths, and infer a MAP action segmentation with the Viterbi algorithm. The resulting action segmentation is used as pseudo-ground truth for estimating our action-level feature embedding and updating the HMM. We alternate the above steps within the Generalized EM framework, which ensures convergence. Our evaluation on the Breakfast, YouTube Instructions, and 50Salads datasets gives superior results to those of the state of the art.
We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures, which showed that plausible new videos could be generated from a single one by stitching its frames together in a novel yet consistent order. This classic work, however, was constrained by its use of hand-designed distance metrics, limiting its use to simple, repetitive videos. We draw on recent techniques from self-supervised learning to learn this distance metric, allowing us to compare frames in a manner that scales to more challenging dynamics, and to condition on other data, such as audio. We learn representations for video frames and frame-to-frame transition probabilities by fitting a video-specific model trained using contrastive learning. To synthesize a texture, we randomly sample frames with high transition probabilities to generate diverse temporally smooth videos with novel sequences and transitions. The model naturally extends to an audio-conditioned setting without requiring any finetuning. Our model outperforms baselines on human perceptual scores, can handle a diverse range of input videos, and can combine semantic and audio-visual cues in order to synthesize videos that synchronize well with an audio signal.
Driving energy consumption plays a major role in the navigation of mobile robots in challenging environments, especially if they are left to operate unattended under limited on-board power. This paper reports on first results of an energy-aware path planner, which can provide estimates of the driving energy consumption and energy recovery of a robot traversing complex uneven terrains. Energy is estimated over trajectories making use of a self-supervised learning approach, in which the robot autonomously learns how to correlate perceived terrain point clouds to energy consumption and recovery. A novel feature of the method is the use of 1D convolutional neural network to analyse the terrain sequentially in the same temporal order as it would be experienced by the robot when moving. The performance of the proposed approach is assessed in simulation over several digital terrain models collected from real natural scenarios, and is compared with a heuristic inclination-based energy model. We show evidence of the benefit of our method to increase the overall prediction r2 score by 66.8% and to reduce the driving energy consumption over planned paths by 5.5%.
This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT). While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging. In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. We observe that instability is a major issue that degrades accuracy, and it can be hidden by apparently good results. We reveal that these results are indeed partial failure, and they can be improved when training is made more stable. We benchmark ViT results in MoCo v3 and several other self-supervised frameworks, with ablations in various aspects. We discuss the currently positive evidence as well as challenges and open questions. We hope that this work will provide useful data points and experience for future research.
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the test-time user, a personalized speech enhancement model can be trained using self-supervised learning. One straightforward approach to model personalization is to use the target speaker's noisy recordings as pseudo-sources. Then, a pseudo denoising model learns to remove injected training noises and recover the pseudo-sources. However, this approach is volatile as it depends on the quality of the pseudo-sources, which may be too noisy. As a remedy, we propose an improvement to the self-supervised approach through data purification. We first train an SNR predictor model to estimate the frame-by-frame SNR of the pseudo-sources. Then, the predictor's estimates are converted into weights which adjust the frame-by-frame contribution of the pseudo-sources towards training the personalized model. We empirically show that the proposed data purification step improves the usability of the speaker-specific noisy data in the context of personalized speech enhancement. Without relying on any clean speech recordings or speaker embeddings, our approach may be seen as privacy-preserving.
This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their enhancement function towards a particular speaker's voice, expecting to solve a narrower problem. Hence, specialists are capable of achieving more optimal performance in addition to reducing computational complexity. However, naive personalization methods can require clean speech from the target user, which is inconvenient to acquire, e.g., due to subpar recording conditions. To this end, we pose personalization as either a zero-shot task, in which no additional clean speech of the target speaker is used for training, or a few-shot learning task, in which the goal is to minimize the duration of the clean speech used for transfer learning. With this paper, we propose self-supervised learning methods as a solution to both zero- and few-shot personalization tasks. The proposed methods are designed to learn the personalized speech features from unlabeled data (i.e., in-the-wild noisy recordings from the target user) without knowing the corresponding clean sources. Our experiments investigate three different self-supervised learning mechanisms. The results show that self-supervised models achieve zero-shot and few-shot personalization using fewer model parameters and less clean data from the target user, achieving the data efficiency and model compression goals.
Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this paper, we explore more general setups where the domain of the unlabeled data for pre-training data differs from the domain of the labeled data for fine-tuning, which in turn may differ from the test data domain. Our experiments show that using target domain data during pre-training leads to large performance improvements across a variety of setups. On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-domain and out-of-domain labeled data by 66%-73%. This has obvious practical implications since it is much easier to obtain unlabeled target domain data than labeled data. Moreover, we find that pre-training on multiple domains improves generalization performance on domains not seen during training. Code and models will be made available at https://github.com/pytorch/fairseq.
We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous methods attempt this by using pixel-level cycle-consistency or feature-level matching losses, but the domain-specific nature of these losses hinder translation across large domain gaps. To address this, we exploit the spatial patterns of self-similarity as a means of defining scene structure. Our spatially-correlative loss is geared towards only capturing spatial relationships within an image rather than domain appearance. We also introduce a new self-supervised learning method to explicitly learn spatially-correlative maps for each specific translation task. We show distinct improvement over baseline models in all three modes of unpaired I2I translation: single-modal, multi-modal, and even single-image translation. This new loss can easily be integrated into existing network architectures and thus allows wide applicability.