Self-supervised learning (SSL) has recently emerged as a powerful approach to learning representations from large-scale unlabeled data, showing promising results in time series analysis. The self-supervised representation learning can be categorized into two mainstream: contrastive and generative. In this paper, we will present a comprehensive comparative study between contrastive and generative methods in time series. We first introduce the basic frameworks for contrastive and generative SSL, respectively, and discuss how to obtain the supervision signal that guides the model optimization. We then implement classical algorithms (SimCLR vs. MAE) for each type and conduct a comparative analysis in fair settings. Our results provide insights into the strengths and weaknesses of each approach and offer practical recommendations for choosing suitable SSL methods. We also discuss the implications of our findings for the broader field of representation learning and propose future research directions. All the code and data are released at \url{https://github.com/DL4mHealth/SSL_Comparison}.
Diabetes is a raising problem that affects many people globally. Diabetic patients are at risk of developing foot ulcer that usually leads to limb amputation, causing significant morbidity, and psychological distress. In order to develop a self monitoring mobile application, it is necessary to be able to classify such ulcers into either of the following classes: Infection, Ischaemia, None, or Both. In this work, we compare the performance of a classical transfer-learning-based method, with the performance of a hybrid classical-quantum Classifier on diabetic foot ulcer classification task. As such, we merge the pre-trained Xception network with a multi-class variational classifier. Thus, after modifying and re-training the Xception network, we extract the output of a mid-layer and employ it as deep-features presenters of the given images. Finally, we use those deep-features to train multi-class variational classifier, where each classifier is implemented on an individual variational circuit. The method is then evaluated on the blind test set DFUC2021. The results proves that our proposed hybrid classical-quantum Classifier leads to considerable improvement compared to solely relying on transfer learning concept through training the modified version of Xception network.
Diabetes is a global raising pandemic. Diabetes patients are at risk of developing foot ulcer that usually leads to limb amputation. In order to develop a self monitoring mobile application, in this work, we propose a novel deep subspace analysis pipeline for semi-supervised diabetic foot ulcer mulit-label classification. To avoid any chance of over-fitting, unlike recent state of the art deep semi-supervised methods, the proposed pipeline dose not include any data augmentation. Whereas, after extracting deep features, in order to make the representation shift invariant, we employ variety of data augmentation methods on each image and generate an image-sets, which is then mapped into a linear subspace. Moreover, the proposed pipeline reduces the cost of retraining when more new unlabelled data become available. Thus, the first stage of the pipeline employs the concept of transfer learning for feature extraction purpose through modifying and retraining a deep convolutional network architect known as Xception. Then, the output of a mid-layer is extracted to generate an image set representer of any given image with help of data augmentation methods. At this stage, each image is transferred to a linear subspace which is a point on a Grassmann Manifold topological space. Hence, to perform analyse them, the geometry of such manifold must be considered. As such, each labelled image is represented as a vector of distances to number of unlabelled images using geodesic distance on Grassmann manifold. Finally, Random Forest is trained for multi-label classification of diabetic foot ulcer images. The method is then evaluated on the blind test set provided by DFU2021 competition, and the result considerable improvement compared to using classical transfer learning with data augmentation.
There has been a substantial amount of research on computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. With recent development and data sharing performed as part of the DFU Challenge (DFUC2020) such a comparison becomes possible: DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training each method and 2,000 images for testing them. The following deep learning-based algorithms are compared in this paper: Faster R-CNN, three variants of Faster R-CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance is obtained Deformable Convolution, a variant of Faster R-CNN, with a mAP of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhanced the F1-Score but not the mAP. Our results show that state-of-the-art deep learning methods can detect DFU with some accuracy, but there are many challenges ahead before they can be implemented in real world settings.
In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this work, we propose a novel domain-adaptive dictionary learning framework for cross-domain visual recognition. Our method generates a set of intermediate domains. These intermediate domains form a smooth path and bridge the gap between the source and target domains. Specifically, we not only learn a common dictionary to encode the domain-shared features, but also learn a set of domain-specific dictionaries to model the domain shift. The separation of the common and domain-specific dictionaries enables us to learn more compact and reconstructive dictionaries for domain adaptation. These dictionaries are learned by alternating between domain-adaptive sparse coding and dictionary updating steps. Meanwhile, our approach gradually recovers the feature representations of both source and target data along the domain path. By aligning all the recovered domain data, we derive the final domain-adaptive features for cross-domain visual recognition. Extensive experiments on three public datasets demonstrates that our approach outperforms most state-of-the-art methods.
Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an iterative method for Keypoint Estimation and Pose prediction of unconstrained faces by Learning Efficient H-CNN Regressors (KEPLER) for addressing the face alignment problem. Recent state of the art methods have shown improvements in face keypoint detection by employing Convolution Neural Networks (CNNs). Although a simple feed forward neural network can learn the mapping between input and output spaces, it cannot learn the inherent structural dependencies. We present a novel architecture called H-CNN (Heatmap-CNN) which captures structured global and local features and thus favors accurate keypoint detecion. HCNN is jointly trained on the visibility, fiducials and 3D-pose of the face. As the iterations proceed, the error decreases making the gradients small and thus requiring efficient training of DCNNs to mitigate this. KEPLER performs global corrections in pose and fiducials for the first four iterations followed by local corrections in the subsequent stage. As a by-product, KEPLER also provides 3D pose (pitch, yaw and roll) of the face accurately. In this paper, we show that without using any 3D information, KEPLER outperforms state of the art methods for alignment on challenging datasets such as AFW and AFLW.
Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstrained face verification problem. Aside from yielding performance improvements, this embedding provides significant advantages in terms of memory and for post-processing operations like subject specific clustering. Experiments on the challenging IJB-A dataset show that the proposed algorithm performs comparably or better than the state of the art methods in verification and identification metrics, while requiring much less training data and training time. The superior performance of the proposed method on the CFP dataset shows that the representation learned by our deep CNN is robust to extreme pose variation. Furthermore, we demonstrate the robustness of the deep features to challenges including age, pose, blur and clutter by performing simple clustering experiments on both IJB-A and LFW datasets.
Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would significantly speed up the training process and possibly improve generalization. Motivated by this objective, we consider the task of adaptively finding concise training subsets which will be iteratively presented to the learner. We use convex optimization methods, based on an objective criterion and feedback from the current performance of the classifier, to efficiently identify informative samples to train on. We propose an algorithm to decompose the optimization problem into smaller per-class problems, which can be solved in parallel. We test our approach on standard classification tasks and demonstrate its effectiveness in decreasing the training set size without compromising performance. We also show that our approach can make the classifier more robust in the presence of label noise and class imbalance.
It is proven that encoding images and videos through Symmetric Positive Definite (SPD) matrices, and considering the Riemannian geometry of the resulting space, can lead to increased classification performance. Taking into account manifold geometry is typically done via embedding the manifolds in tangent spaces, or Reproducing Kernel Hilbert Spaces (RKHS). Recently, it was shown that embedding such manifolds into a Random Projection Spaces (RPS), rather than RKHS or tangent space, leads to higher classification and clustering performance. However, based on structure and dimensionality of the randomly generated hyperplanes, the classification performance over RPS may vary significantly. In addition, fine-tuning RPS is data expensive (as it requires validation-data), time consuming, and resource demanding. In this paper, we introduce an approach to learn an optimized kernel-based projection (with fixed dimensionality), by employing the concept of subspace clustering. As such, we encode the association of data points to the underlying subspace of each point, to generate meaningful hyperplanes. Further, we adopt the concept of dictionary learning and sparse coding, and discriminative analysis, for the optimized kernel-based projection space (OPS) on SPD manifolds. We validate our algorithm on several classification tasks. The experiment results also demonstrate that the proposed method outperforms state-of-the-art methods on such manifolds.