`

Timezone: »

 
Poster
CliqueCNN: Deep Unsupervised Exemplar Learning
Miguel A Bautista · Artsiom Sanakoyeu · Ekaterina Tikhoncheva · Bjorn Ommer

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #156 #None

Exemplar learning is a powerful paradigm for discovering visual similarities in an unsupervised manner. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of convolutional neural networks is impaired. Given weak estimates of local distance we propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact cliques. Learning exemplar similarities is framed as a sequence of clique categorization tasks. The CNN then consolidates transitivity relations within and between cliques and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification.

Author Information

Miguel A Bautista (Heidelberg University)
Artsiom Sanakoyeu (Heidelberg University)
Ekaterina Tikhoncheva (Heidelberg University)
Bjorn Ommer (Heidelberg University)

More from the Same Authors