Unified Attention Network (UAN)
We propose a new architecture that learns to attend to different Convolutional Neural Networks (CNN) layers (i.e., different levels of abstraction) and different spatial locations (i.e., specific layers within a given feature map) in a sequential manner to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) timestep, a CNN layer is selected and its output is processed by a spatial soft-attention mechanism. We refer to this architecture as the Unified Attention Network (UAN), since it combines the ‘what’ and ‘where’ aspects of attention, i.e., ‘what’ level of abstraction to attend to, and ‘where’ should the network look at. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based camera pose and orientation regression and (ii) indoor scene classification. We evaluate our method on standard benchmarks for camera localization (Cambridge, 7-Scene, and TUM-LSI datasets) and for scene classification (MIT-67 indoor dataset), and show that our method improves upon the results of previous methods. Empirically, we show that combining ‘what’ and ‘where’ aspects of attention improves network performance on both tasks. …

ClusART
Topic detection becomes more important due to the increase of information electronically available and the necessity to process and filter it. In this context our master’s thesis work was carried out, where we proposed to present a new approach to the detection of topics called ClusART. Thus, we proposed a three-phase approach, namely : a first phase during which lexical preprocessing was conducted. A second phase during which the construction and generation of vectors representing the documents was carried out. A third phase which is itself composed of two steps. In the first step we used the FuzzyART algorithm for the training phase. In the second step we used a classifier using Paragraph Vector for the test phase. The comparative study of our approach on the 20 Newsgroups dataset showed that our approach is able to detect almost relevant topics. …

Segregation Network
The problem of multiple class novelty detection is gaining increasing importance due to the large availability of multimedia data and the increasing requirement of the classification models to work in an open set scenario. To this end, novelty detection tries to answer this important question: given a test example should we even try to classify it? In this work, we design a novel deep learning framework, termed Segregation Network, which is trained using the mixup technique. We construct interpolated points using convex combinations of pairs of training data and use our novel loss function for prediction of its constituent classes. During testing, for each input query, mixed samples with the known class prototypes are generated and passed through the proposed network. The output of the network reveals the constituent classes which can be used to determine whether the incoming data is from the known class set or not. Our algorithm is trained using just the data from the known classes and does not require any auxiliary dataset or attributes. Extensive evaluation on two benchmark datasets namely Caltech-256 and Stanford Dogs and comparison with the state-of-the-art justifies the effectiveness of the proposed framework. …

Adversarial Robustness Toolbox (ART)
Adversarial examples have become an indisputable threat to the security of modern AI systems based on deep neural networks (DNNs). The Adversarial Robustness Toolbox (ART) is a Python library designed to support researchers and developers in creating novel defence techniques, as well as in deploying practical defences of real-world AI systems. Researchers can use ART to benchmark novel defences against the state-of-the-art. For developers, the library provides interfaces which support the composition of comprehensive defence systems using individual methods as building blocks. The Adversarial Robustness Toolbox supports machine learning models (and deep neural networks (DNNs) specifically) implemented in any of the most popular deep learning frameworks (TensorFlow, Keras, PyTorch). Currently, the library is primarily intended to improve the adversarial robustness of visual recognition systems, however, future releases that will comprise adaptations to other data modes (such as speech, text or time series) are envisioned. The ART source code is released (https://…/adversarial-robustness-toolbox ) under an MIT license. The release includes code examples and extensive documentation (http://adversarial-robustness-toolbox.readthedocs.io ) to help researchers and developers get quickly started. …