This paper proposes the "double attention block" to aggregate and propagate informative global features from the entire spatio/spatio-temporal space of input. Specifically, the model first generates a set of attention distributions over the input and obtains a set of global feature vectors based on the attention. Then, for each input position, it generates another attention distribution over the set of global feature vectors and uses this to aggregate those global feature vectors into a position-specific feature vector. The proposed component can be easily plugged into existing architectures. Experiments on image recognition (ImageNet-1k) and video classification (Kinetics, UCF-101) show that the proposed model outperforms the baselines and is more efficient.

Modern machine learning techniques have been extensively applied to materials science, especially for property prediction tasks. A majority of these methods address scalar property predictions, while more challenging spectral properties remain less emphasized. We formulate a crystal-to-sequence learning task and propose a novel attention-based learning method, Xtal2DoS, which decodes the sequential representation of the material density of states (DoS) properties by incorporating the learned atomic embeddings through attention networks. Experiments show Xtal2DoS is faster than the existing models, and consistently outperforms other state-of-the-art methods on four metrics for two fundamental spectral properties, phonon and electronic DoS.

While camera and LiDAR processing have been revolutionized since the introduction of deep learning, radar processing still relies on classical tools. In this paper, we introduce a deep learning approach for radar processing, working directly with the radar complex data. To overcome the lack of radar labeled data, we rely in training only on the radar calibration data and introduce new radar augmentation techniques. We evaluate our method on the radar 4D detection task and demonstrate superior performance compared to the classical approaches while keeping real-time performance. Applying deep learning on radar data has several advantages such as eliminating the need for an expensive radar calibration process each time and enabling classification of the detected objects with almost zero-overhead.

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the input image at different stages in the CNN pipeline, and outputs a 2D matrix of scores for each map. Standard CNN architectures are modified through the incorporation of this module, and trained under the constraint that a convex combination of the intermediate 2D feature vectors, as parameterised by the score matrices, must \textit{alone} be used for classification. Incentivised to amplify the relevant and suppress the irrelevant or misleading, the scores thus assume the role of attention values. Our experimental observations provide clear evidence to this effect: the learned attention maps neatly highlight the regions of interest while suppressing background clutter. Consequently, the proposed function is able to bootstrap standard CNN architectures for the task of image classification, demonstrating superior generalisation over 6 unseen benchmark datasets. When binarised, our attention maps outperform other CNN-based attention maps, traditional saliency maps, and top object proposals for weakly supervised segmentation as demonstrated on the Object Discovery dataset. We also demonstrate improved robustness against the fast gradient sign method of adversarial attack.

We propose a perceptron-style algorithm for fast discriminative training of structured latent variable model. This method extends the perceptron algorithm for the learning with latent dependencies, as an alternative to existing probabilistic latent variable models. It relies on Viterbi decoding over latent variables, combined with simple additive updates. Its training cost is significantly lower than that of probabilistic latent variable models, while it gives comparable or even superior classification accuracy on our tasks. Experiments on natural language processing problems demonstrate that its results are among those good reports on corresponding data sets.