Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Domain-Adaptive Deep Network Compression

  • Masana, Marc|||0000-0003-3254-3096
  • Weijer, Joost van de|||0000-0002-9656-9706
  • Herranz, Luis|||0000-0002-7022-3395
  • Bagdanov, Andrew|||0000-0001-6408-7043
  • Alvarez, Jose M.
Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer. We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing. We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone - with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

GTCreator, a flexible annotation tool for image-based datasets

  • Bernal del Nozal, Jorge|||0000-0001-8493-9514
  • Histace, Aymeric|||0000-0002-3029-4412
  • Masana, Marc|||0000-0003-3254-3096
  • Angermann, Quentin
  • Sánchez Montes, Cristina|||0000-0002-9692-9521
  • Rodríguez De Miguel, Cristina|||0000-0002-5576-0854
  • Hammami, Maroua
  • García-Rodríguez, Ana
  • Córdova, Henry|||0000-0002-6636-6764
  • Romain, Olivier
  • Fernández-Esparrach, Gloria|||0000-0002-3378-3940
  • Dray, Xavier
  • Sánchez, F. Javier|||0000-0002-9364-3122
Purpose:: Methodology evaluation for decision support systems for health is a time-consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use. Methods:: We introduce GTCreator, a flexible annotation tool for providing image and text annotations to image-based datasets. It keeps the main basic functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing and easy annotation transfer aiming to speed up annotation processes in large datasets. Results:: The comparison with other similar tools shows that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites. Conclusion:: Our proposed annotation tool has been proven to be efficient for large image dataset annotation, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis.