2 Hits in 6.5 sec

Recognizing Food Places in Egocentric Photo-streams using Multi-scale Atrous Convolutional Networks and Self-Attention Mechanism

Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Farhan Akram, Estefania Talavera, Syeda Furruka Banu, Petia Radeva, Domenec Puig
2019 IEEE Access  
In this paper, we propose a self-attention mechanism with multi-scale atrous convolutional networks to generate discriminative features from image streams to recognize a predetermined set of food place  ...  Consequently, developing an automated monitoring system based on analyzing a person's food habits from daily recorded egocentric photo-streams of the food places can provide valuable means for people to  ...  multi-scale Atrous convolutional networks [12] , called MACNet with self-attention (MACNet+SA) for improving classification rate of food places. • Application of the MACNet+SA model to treat a sequence  ... 
doi:10.1109/access.2019.2902225 fatcat:rvcmtnzao5hvplko3ycjnc7vka

Playing to distraction: towards a robust training of CNN classifiers through visual explanation techniques [article]

David Morales, Estefania Talavera, Beatriz Remeseiro
2021 arXiv   pre-print
We tested the proposed approach by embedding it into the learning process of a convolutional neural network for the analysis and classification of two well-known datasets, namely Stanford cars and FGVC-Aircraft  ...  Unlike the attention mechanisms that focus on the relevant parts of images, we aim to improve the robustness of the model by making it pay attention to other regions as well.  ...  Acknowledgements We would like to thank the Center for Information Technology of the University of Groningen for their support and for providing access to the Peregrine high performance computing cluster  ... 
arXiv:2012.14173v2 fatcat:swhnlwi4tnfjbpcjddnij54sui