In the context of localization, however, there is no natural definition of classes. Therefore, images areartificially separated intopositive/negativeclasses with respect to the chosen anchor images, based on some geometric proximity measure.

Labeling has always been expensive in the medical context, which has hindered related deep learning application. Our work introduces active learning in surgical video frame selection to construct a high-quality, affordable Laparoscopic Cholecystectomy dataset for semantic segmentation. Active learning allows the Deep Neural Networks (DNNs) learning pipeline to include the dataset construction workflow, which means DNNs trained by existing dataset will identify the most informative data from the newly collected data. At the same time, DNNs' performance and generalization ability improve over time when the newly selected and annotated data are included in the training data. We assessed different data informativeness measurements and found the deep features distances select the most informative data in this task. Our experiments show that with half of the data selected by active learning, the DNNs achieve almost the same performance with 0.4349 mean Intersection over Union (mIoU) compared to the same DNNs trained on the full dataset (0.4374 mIoU) on the critical anatomies and surgical instruments.

Accurate people counting in smart buildings and intelligent transportation systems is crucial for energy management, safety protocols, and resource allocation. This is especially critical during emergencies, where precise occupant counts are vital for safe evacuation. Existing methods struggle with large crowds, often losing accuracy with even a few additional people. To address this limitation, this study proposes a novel approach combining a new object tracking algorithm, a novel counting algorithm, and a fine-tuned object detection model. This method achieves 97% accuracy in real-time people counting with a frame rate of 20-27 FPS on a low-power edge computer.

Machine unlearning is new emerged technology that removes a subset of the training data from a trained model without affecting the model performance on the remaining data. This topic is becoming increasingly important in protecting user privacy and eliminating harmful or outdated data. The key challenge lies in effectively and efficiently unlearning specific information without compromising the model's utility on the retained data. For the pre-trained models, fine-tuning is an important way to achieve the unlearning target. Previous work typically fine-tuned the entire model's parameters, which incurs significant computation costs. In addition, the fine-tuning process may cause shifts in the intermediate layer features, affecting the model's overall utility. In this work, we propose a novel and efficient machine unlearning method on pre-trained models. We term the method as Residual Feature Alignment Unlearning. Specifically, we leverage LoRA (Low-Rank Adaptation) to decompose the model's intermediate features into pre-trained features and residual features. By adjusting the residual features, we align the unlearned model with the pre-trained model at the intermediate feature level to achieve both unlearning and remaining targets. The method aims to learn the zero residuals on the retained set and shifted residuals on the unlearning set. Extensive experiments on numerous datasets validate the effectiveness of our approach.

In medical imaging, the aim is often to place a 2D image in a 3D volumetric observation to w. Current approaches for rigid single slice in volume registration are limited by requirements such as pose initialization, stacks of adjacent slices, or reliable anatomical landmarks. Here, we propose a self-supervised 2D/3D registration approach to match a single 2D slice to the corresponding 3D volume. The method works in data without anatomical priors such as images of tumors. It addresses the dimensionality disparity and establishes correspondences between 2D in-plane and 3D out-of-plane rotation-equivariant features by using group equivariant CNNs. These rotation-equivariant features are extracted from the 2D query slice and aligned with their 3D counterparts. Results demonstrate the robustness of the proposed slice-in-volume registration on the NSCLC-Radiomics CT and KIRBY21 MRI datasets, attaining an absolute median angle error of less than 2 degrees and a mean-matching feature accuracy of 89% at a tolerance of 3 pixels.

Graph neural networks (GNNs) have emerged as powerful tools for processing relational data in applications. However, GNNs suffer from the problem of oversmoothing, the property that the features of all nodes exponentially converge to the same vector over layers, prohibiting the design of deep GNNs. In this work we study oversmoothing in graph convolutional networks (GCNs) by using their Gaussian process (GP) equivalence in the limit of infinitely many hidden features. By generalizing methods from conventional deep neural networks (DNNs), we can describe the distribution of features at the output layer of deep GCNs in terms of a GP: as expected, we find that typical parameter choices from the literature lead to oversmoothing. The theory, however, allows us to identify a new, nonoversmoothing phase: if the initial weights of the network have sufficiently large variance, GCNs do not oversmooth, and node features remain informative even at large depth. We demonstrate the validity of this prediction in finite-size GCNs by training a linear classifier on their output. Moreover, using the linearization of the GCN GP, we generalize the concept of propagation depth of information from DNNs to GCNs. This propagation depth diverges at the transition between the oversmoothing and non-oversmoothing phase. We test the predictions of our approach and find good agreement with finite-size GCNs. Initializing GCNs near the transition to the non-oversmoothing phase, we obtain networks which are both deep and expressive.

Special-purpose Autonomous Underwater Vehicles (AUVs) are utilised for benthic (seafloor) surveys, where the vehicle collects optical imagery of the seafloor. Due to the small-sensor footprint of the cameras and the vast areas to be surveyed, these AUVs can not feasibly collect full coverage imagery of areas larger than a few tens of thousands of square meters. Therefore it is necessary for AUV paths to sample the surveys areas sparsely, yet effectively. Broad-scale acoustic bathymetric data is readily available over large areas, and is often a useful prior of seafloor cover. As such, prior bathymetry can be used to guide AUV data collection. This research proposes methods for planning initial AUV surveys that efficiently explore a feature space representation of the bathymetry, in order to sample from a diverse set of bathymetric terrain. This will enable the AUV to visit areas that likely contain unique habitats and are representative of the entire survey site. We propose several information gathering planners that utilise a feature space exploration reward, to plan freeform paths or to optimise the placement of a survey template. The suitability of these methods to plan AUV surveys is evaluated based on the coverage of the feature space and also the ability to visit all classes of benthic habitat on the initial dive. Informative planners based on Rapidly-expanding Random Trees (RRT) and Monte-Carlo Tree Search (MCTS) were found to be the most effective. This is a valuable tool for AUV surveys as it increases the utility of initial dives. It also delivers a comprehensive training set to learn a relationship between acoustic bathymetry and visually-derived seafloor classifications.

Efficient and effective Out-of-Distribution (OOD) detection is essential for the safe deployment of AI in latency-critical applications. Recently, studies have revealed that detecting OOD based on feature space information can be highly effective. Despite their effectiveness, however, exiting feature space OOD methods may incur non-negligible computational overhead, given their reliance on auxiliary models built from training features. In this paper, we aim to obviate auxiliary models to optimize computational efficiency while leveraging the rich information embedded in the feature space. We investigate from the novel perspective of decision boundaries and propose to detect OOD using the feature distance to decision boundaries. To minimize the cost of measuring the distance, we introduce an efficient closed-form estimation, analytically proven to tightly lower bound the distance. We observe that ID features tend to reside further from the decision boundaries than OOD features. Our observation aligns with the intuition that models tend to be more decisive on ID samples, considering that distance to decision boundaries quantifies model uncertainty. From our understanding, we propose a hyperparameter-free, auxiliary model-free OOD detector. Our OOD detector matches or surpasses the effectiveness of state-of-the-art methods across extensive experiments. Meanwhile, our OOD detector incurs practically negligible overhead in inference latency. Overall, we significantly enhance the efficiency-effectiveness trade-off in OOD detection.

Human-robot interaction (HRI) has become a crucial enabler in houses and industries for facilitating operational flexibility. When it comes to mobile collaborative robots, this flexibility can be further increased due to the autonomous mobility and navigation capacity of the robotic agents, expanding their workspace and consequently, the personalizable assistance they can provide to the human operators. This however requires that the robot is capable of detecting and identifying the human counterpart in all stages of the collaborative task, and in particular while following a human in crowded workplaces. To respond to this need, we developed a unified perception and navigation framework, which enables the robot to identify and follow a target person using a combination of visual Re-Identification (Re-ID), hand gestures detection, and collision-free navigation. The Re-ID module can autonomously learn the features of a target person and use the acquired knowledge to visually re-identify the target. The navigation stack is used to follow the target avoiding obstacles and other individuals in the environment. Experiments are conducted with few subjects in a laboratory setting where some unknown dynamic obstacles are introduced.