This paper presents an innovative deep learning pipeline which estimates the relative pose of a spacecraft by incorporating the temporal information from a rendezvous sequence. It leverages the performance of long short-term memory (LSTM) units in modelling sequences of data for the processing of features extracted by a convolutional neural network (CNN) backbone. Three distinct training strategies, which follow a coarse-to-fine funnelled approach, are combined to facilitate feature learning and improve end-to-end pose estimation by regression. The capability of CNNs to autonomously ascertain feature representations from images is exploited to fuse thermal infrared data with red-green-blue (RGB) inputs, thus mitigating the effects of artefacts from imaging space objects in the visible wavelength. Each contribution of the proposed framework, dubbed ChiNet, is demonstrated on a synthetic dataset, and the complete pipeline is validated on experimental data.

Automatic Speech Recognition (ASR) is an active field of research due to its huge number of applications and the proliferation of interfaces or computing devices that can support speech processing. But the bulk of applications is based on well-resourced languages that overshadow under-resourced ones. Yet ASR represents an undeniable mean to promote such languages, especially when design human-to-human or human-to-machine systems involving illiterate people. An approach to design an ASR system targeting under-resourced languages is to start with a limited vocabulary. ASR using a limited vocabulary is a subset of the speech recognition problem that focuses on the recognition of a small number of words or sentences. This paper aims to provide a comprehensive view of mechanisms behind ASR systems as well as techniques, tools, projects, recent contributions, and possibly future directions in ASR using a limited vocabulary. This work consequently provides a way to go when designing ASR system using limited vocabulary. Although an emphasis is put on limited vocabulary, most of the tools and techniques reported in this survey applied to ASR systems in general.

The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models. First efforts in FL focused on learning a single global model with good average performance across clients, but the global model may be arbitrarily bad for a given client, due to the inherent heterogeneity of local data distributions. Federated multi-task learning (MTL) approaches can learn personalized models by formulating an opportune penalized optimization problem. The penalization term can capture complex relations among personalized models, but eschews clear statistical assumptions about local data distributions. In this work, we propose to study federated MTL under the flexible assumption that each local data distribution is a mixture of unknown underlying distributions. This assumption encompasses most of the existing personalized FL approaches and leads to federated EM-like algorithms for both client-server and fully decentralized settings. Moreover, it provides a principled way to serve personalized models to clients not seen at training time. The algorithms' convergence is analyzed through a novel federated surrogate optimization framework, which can be of general interest. Experimental results on FL benchmarks show that in most cases our approach provides models with higher accuracy and fairness than state-of-the-art methods.

We propose an information-fusion approach based on belief functions to combine convolutional neural networks. In this approach, several pre-trained DS-based CNN architectures extract features from input images and convert them into mass functions on different frames of discernment. A fusion module then aggregates these mass functions using Dempster's rule. An end-to-end learning procedure allows us to fine-tune the overall architecture using a learning set with soft labels, which further improves the classification performance. The effectiveness of this approach is demonstrated experimentally using three benchmark databases.

Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are susceptible to be fooled with nearly high confidence by an adversary. In practice, the vulnerability of deep learning systems against carefully perturbed images, known as adversarial examples, poses a dire security threat in the physical world applications. To address this phenomenon, we present, what to our knowledge, is the first ever image set based adversarial defence approach. Image set classification has shown an exceptional performance for object and face recognition, owing to its intrinsic property of handling appearance variability. We propose a robust deep Bayesian image set classification as a defence framework against a broad range of adversarial attacks. We extensively experiment the performance of the proposed technique with several voting strategies. We further analyse the effects of image size, perturbation magnitude, along with the ratio of perturbed images in each image set. We also evaluate our technique with the recent state-of-the-art defence methods, and single-shot recognition task. The empirical results demonstrate superior performance on CIFAR-10, MNIST, ETH-80, and Tiny ImageNet datasets.

Accurate detection of a drivers attention state can help develop assistive technologies that respond to unexpected hazards in real time and therefore improve road safety. This study compares the performance of several attention classifiers trained on participants brain activity. Participants performed a driving task in an immersive simulator where the car randomly deviated from the cruising lane. They had to correct the deviation and their response time was considered as an indicator of attention level. Participants repeated the task in two sessions; in one session they received kinesthetic feedback and in another session no feedback. Using their EEG signals, we trained three attention classifiers; a support vector machine (SVM) using EEG spectral band powers, and a Convolutional Neural Network (CNN) using either spectral features or the raw EEG data. Our results indicated that the CNN model trained on raw EEG data obtained under kinesthetic feedback achieved the highest accuracy (89%). While using a participants own brain activity to train the model resulted in the best performances, inter-subject transfer learning still performed high (75%), showing promise for calibration-free Brain-Computer Interface (BCI) systems. Our findings show that CNN and raw EEG signals can be employed for effective training of a passive BCI for real-time attention classification.

Due to the rapid increase in the diversity of image data, the problem of domain generalization has received increased attention recently. While domain generalization is a challenging problem, it has achieved great development thanks to the fast development of AI techniques in computer vision. Most of these advanced algorithms are proposed with deep architectures based on convolution neural nets (CNN). However, though CNNs have a strong ability to find the discriminative features, they do a poor job of modeling the relations between different locations in the image due to the response to CNN filters are mostly local. Since these local and global spatial relationships are characterized to distinguish an object under consideration, they play a critical role in improving the generalization ability against the domain gap. In order to get the object parts relationships to gain better domain generalization, this work proposes to use the self attention model. However, the attention models are proposed for sequence, which are not expert in discriminate feature extraction for 2D images. Considering this, we proposed a hybrid architecture to discover the spatial relationships between these local features, and derive a composite representation that encodes both the discriminative features and their relationships to improve the domain generalization. Evaluation on three well-known benchmarks demonstrates the benefits of modeling relationships between the features of an image using the proposed method and achieves state-of-the-art domain generalization performance. More specifically, the proposed algorithm outperforms the state-of-the-art by $2.2\%$ and $3.4\%$ on PACS and Office-Home databases, respectively.

This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing deep metric learning methods learn an embedding space with a general objective of increasing interclass distances and decreasing intraclass distances. However, the conventional losses of metric learning usually suppress intraclass variations which might be helpful to identify samples of unseen classes. To address this problem, we propose to adaptively learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. We further employ a relational module to capture the correlations among each feature in the ensemble and construct a graph to represent an image. We then perform relational inference on the graph to integrate the ensemble and obtain a relation-aware embedding to measure the similarities. Extensive experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.

Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the network from learning it, recognizing the bias type in the real dataset is often prohibitive. This paper proposes a novel bias-tailored augmentation-based approach, BiaSwap, for learning debiased representation without requiring supervision on the bias type. Assuming that the bias corresponds to the easy-to-learn attributes, we sort the training images based on how much a biased classifier can exploits them as shortcut and divide them into bias-guiding and bias-contrary samples in an unsupervised manner. Afterwards, we integrate the style-transferring module of the image translation model with the class activation maps of such biased classifier, which enables to primarily transfer the bias attributes learned by the classifier. Therefore, given the pair of bias-guiding and bias-contrary, BiaSwap generates the bias-swapped image which contains the bias attributes from the bias-contrary images, while preserving bias-irrelevant ones in the bias-guiding images. Given such augmented images, BiaSwap demonstrates the superiority in debiasing against the existing baselines over both synthetic and real-world datasets. Even without careful supervision on the bias, BiaSwap achieves a remarkable performance on both unbiased and bias-guiding samples, implying the improved generalization capability of the model.

Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs. However, most existing methods fail to recover realistic structures due to over-smoothing of fine-grained details. In this paper, we develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN). We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges. This decoupled architecture together with a multiscale grid feature learning is able to generate more realistic on-surface details. We evaluate our model on the Figure 1: We propose an edge-guiding and voxel-based publicly available completion datasets and show that it point cloud completion network to reconstruct complete outperforms existing state-of-the-art approaches quantitatively points from incomplete inputs.