This paper presents parametric instance classification (PIC) forunsupervised visual feature learning.

These methods giveeffectiverepresentations and decent results ofdownstream tasks, however we suggest that utilizing other nature characteristics of video can lead to different yet representative video representations.

Group Recommendation (GR), which aims to recommend items to groups of users, has become a promising and practical direction for recommendation systems.

Electrocardiogram (ECG), as a crucial find-grained cardiac feature, has been successfully recovered from radar signals in the literature, but the performance heavily relies on the high-quality radar signal and numerous radar-ECG pairs for training, restricting the applications in new scenarios due to data scarcity. Therefore, this work will focus on radar-based ECG recovery in new scenarios with limited data and propose a cardio-focusing and -tracking (CFT) algorithm to precisely track the cardiac location to ensure an efficient acquisition of high-quality radar signals. Furthermore, a transfer learning model (RFcardi) is proposed to extract cardio-related information from the radar signal without ECG ground truth based on the intrinsic sparsity of cardiac features, and only a few synchronous radar-ECG pairs are required to fine-tune the pre-trained model for the ECG recovery. The experimental results reveal that the proposed CFT can dynamically identify the cardiac location, and the RFcardi model can effectively generate faithful ECG recoveries after using a small number of radar-ECG pairs for training. The code and dataset are available after the publication.

Group Recommendation (GR), which aims to recommend items to groups of users, has become a promising and practical direction for recommendation systems. To this end, we present a novel unsupervised group recommendation framework named \underline{\text{I}} dentify \underline{\text{T}} hen \underline{\text{R}} ecommend ( \underline{\text{ITR}}), where it first identifies the user groups in an unsupervised manner even without the pre-defined number of groups, and then two pre-text tasks are designed to conduct self-supervised group recommendation. Concretely, at the group identification stage, we first estimate the adaptive density of each user point, where areas with higher densities are more likely to be recognized as group centers. Then, a heuristic merge-and-split strategy is designed to discover the user groups and decision boundaries. Subsequently, at the self-supervised learning stage, the pull-and-repulsion pre-text task is proposed to optimize the user-group distribution.

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can aggregate contextual information for downstream tasks. But, existing MAE pre-training methods, which were specifically developed with the ViT architecture, lack the ability to capture geometric shape and spatial information, which is critical for medical image segmentation tasks. In this paper, we propose a novel extension of known MAEs for self pre-training (i.e., models pre-trained on the same target dataset) for 3D medical image segmentation. (1) We propose a new topological loss to preserve geometric shape information by computing topological signatures of both the input and reconstructed volumes, learning geometric shape information. (2) We introduce a pre-text task that predicts the positions of the centers and eight corners of 3D crops, enabling the MAE to aggregate spatial information. (3) We extend the MAE pre-training strategy to a hybrid state-of-the-art (SOTA) medical image segmentation architecture and co-pretrain it alongside the ViT. (4) We develop a fine-tuned model for downstream segmentation tasks by complementing the pre-trained ViT encoder with our pre-trained SOTA model. Extensive experiments on five public 3D segmentation datasets show the effectiveness of our new approach.

Precise localization is critical for autonomous vehicles. We present a self-supervised learning method that employs Transformers for the first time for the task of outdoor localization using LiDAR data. We propose a pre-text task that reorganizes the slices of a $360^\circ$ LiDAR scan to leverage its axial properties. Our model, called Slice Transformer, employs multi-head attention while systematically processing the slices. To the best of our knowledge, this is the first instance of leveraging multi-head attention for outdoor point clouds. We additionally introduce the Perth-WA dataset, which provides a large-scale LiDAR map of Perth city in Western Australia, covering $\sim$4km$^2$ area. Localization annotations are provided for Perth-WA. The proposed localization method is thoroughly evaluated on Perth-WA and Appollo-SouthBay datasets. We also establish the efficacy of our self-supervised learning approach for the common downstream task of object classification using ModelNet40 and ScanNN datasets. The code and Perth-WA data will be publicly released.

With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life (RUL) predictions. However, one of the major challenges for DL techniques resides in the difficulty of obtaining large amounts of labelled data on industrial systems. To overcome this lack of labelled data, an emerging learning technique is considered in our work: Self-Supervised Learning, a sub-category of unsupervised learning approaches. This paper aims to investigate whether pre-training DL models in a self-supervised way on unlabelled sensors data can be useful for RUL estimation with only Few-Shots Learning, i.e. with scarce labelled data. In this research, a fatigue damage prognostics problem is addressed, through the estimation of the RUL of aluminum alloy panels (typical of aerospace structures) subject to fatigue cracks from strain gauge data. Synthetic datasets composed of strain data are used allowing to extensively investigate the influence of the dataset size on the predictive performance. Results show that the self-supervised pre-trained models are able to significantly outperform the non-pre-trained models in downstream RUL prediction task, and with less computational expense, showing promising results in prognostic tasks when only limited labelled data is available.