Timezone: »
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 (University of Munich)
More from the Same Authors
-
2022 Poster: VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids »
Albert Pumarola · Artsiom Sanakoyeu · Lior Yariv · Ali Thabet · Yaron Lipman -
2021 Poster: Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning »
Timo Milbich · Karsten Roth · Samarth Sinha · Ludwig Schmidt · Marzyeh Ghassemi · Bjorn Ommer -
2021 Poster: ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis »
Patrick Esser · Robin Rombach · Andreas Blattmann · Bjorn Ommer -
2020 Poster: Network-to-Network Translation with Conditional Invertible Neural Networks »
Robin Rombach · Patrick Esser · Bjorn Ommer -
2020 Oral: Network-to-Network Translation with Conditional Invertible Neural Networks »
Robin Rombach · Patrick Esser · Bjorn Ommer -
2012 Poster: Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity »
Angela Eigenstetter · Bjorn Ommer