-
Chapter and Conference Paper
Exploring the Challenges Towards Lifelong Fact Learning
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and clo...
-
Chapter and Conference Paper
Memory Aware Synapses: Learning What (not) to Forget
Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial le...
-
Chapter
Unsupervised Domain Adaptation Based on Subspace Alignment
Subspace-based domain adaptation methods have been very successful in the context of image recognition. In this chapter, we discuss methods using Subspace Alignment (SA). They are based on a map** function w...
-
Chapter and Conference Paper
Who’s that Actor? Automatic Labelling of Actors in TV Series Starting from IMDB Images
In this work, we aim at automatically labeling actors in a TV series. Rather than relying on transcripts and subtitles, as has been demonstrated in the past, we show how to achieve this goal starting from a se...
-
Chapter and Conference Paper
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (...
-
Chapter and Conference Paper
Transfer Learning for Prostate Cancer Map** Based on Multicentric MR Imaging Databases
This paper addresses the issue of fusing datasets coming from different imaging protocols or scanners to boost the performance of computer aided diagnostic system. We present novel contributions in the field o...
