University of Trento

About: University of Trento is a education organization based out in Trento, Italy. It is known for research contribution in the topics: Population & Context (language use). The organization has 10527 authors who have published 30978 publications receiving 896614 citations. The organization is also known as: Universitá degli Studi di Trento & Universita degli Studi di Trento.

Decoding Representations of Face Identity That are Tolerant to Rotation

Abstract: In order to recognize the identity of a face we need to distinguish very similar images (specificity) while also generalizing identity information across image transformations such as changes in orientation (tolerance). Recent studies investigated the representation of individual faces in the brain, but it remains unclear whether the human brain regions that were found encode representations of individual images (specificity) or face identity (specificity plus tolerance). In the present article, we use multivoxel pattern analysis in the human ventral stream to investigate the representation of face identity across rotations in depth, a kind of transformation in which no point in the face image remains unchanged. The results reveal representations of face identity that are tolerant to rotations in depth in occipitotemporal cortex and in anterior temporal cortex, even when the similarity between mirror symmetrical views cannot be used to achieve tolerance. Converging evidence from different analysis techniques shows that the right anterior temporal lobe encodes a comparable amount of identity information to occipitotemporal regions, but this information is encoded over a smaller extent of cortex.

Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss

Abstract: A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.

Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery

Abstract: Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to learn a joint spectral–spatial–temporal feature representation in a unified framework for change detection in multispectral images. To this end, we bring together a convolutional neural network and a recurrent neural network into one end-to-end network. The former is able to generate rich spectral-spatial feature representations, while the latter effectively analyzes temporal dependence in bitemporal images. In comparison with previous approaches to change detection, the proposed network architecture possesses three distinctive properties: 1) it is end-to-end trainable, in contrast to most existing methods whose components are separately trained or computed; 2) it naturally harnesses spatial information that has been proven to be beneficial to change detection task; and 3) it is capable of adaptively learning the temporal dependence between multitemporal images, unlike most of the algorithms that use fairly simple operation like image differencing or stacking. As far as we know, this is the first time that a recurrent convolutional network architecture has been proposed for multitemporal remote sensing image analysis. The proposed network is validated on real multispectral data sets. Both visual and quantitative analyses of the experimental results demonstrate competitive performance in the proposed mode.

Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation

Abstract: Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map. The proposed SelectionGAN explicitly utilizes the semantic information and consists of two stages. In the first stage, the condition image and the target semantic map are fed into a cycled semantic-guided generation network to produce initial coarse results. In the second stage, we refine the initial results by using a multi-channel attention selection mechanism. Moreover, uncertainty maps automatically learned from attentions are used to guide the pixel loss for better network optimization. Extensive experiments on Dayton, CVUSA and Ego2Top datasets show that our model is able to generate significantly better results than the state-of-the-art methods. The source code, data and trained models are available at https://github.com/Ha0Tang/SelectionGAN.

Prestimulus oscillatory power and connectivity patterns predispose conscious somatosensory perception

Abstract: Which aspects of our sensory environment enter conscious awareness does not only depend on physical features of the stimulus, but also critically on the so-called current brain state. Results from magnetoencephalography/EEG studies using near-threshold stimuli have consistently pointed to reduced levels of α- (8–12 Hz) power in relevant sensory areas to predict whether a stimulus will be consciously perceived or not. These findings have been mainly interpreted in strictly “local” terms of enhanced excitability of neuronal ensembles in respective cortical regions. The present study aims to introduce a framework that complements this rather local perspective, by stating that the functional connectivity architecture before stimulation will predetermine information flow. Thus, information computed at a local level will be distributed throughout a network, thereby becoming consciously accessible. Data from a previously published experiment on conscious somatosensory near-threshold perception was reanalyzed focusing on the prestimulus period. Analysis of spectral power showed reduced α-power mainly in the contralateral S2 and middle frontal gyrus to precede hits, thus overall supporting the current literature. Furthermore, differences between hits and misses were obtained on global network (graph theoretical) features in the same interval. Most importantly, in accordance with our framework, we could show that the somatosensory cortex is “more efficiently” integrated into a distributed network in the prestimulus period. This finding means that when a relevant sensory stimulus impinges upon the system, it will encounter preestablished pathways for information flow. In this sense, prestimulus functional connectivity patterns form “windows” to conscious perception.