ASAP DML: Deep Metric Learning with Alternating Sets of Alternating Proxies

no code implementations • 29 Sep 2021 • Yeti Z. Gürbüz, Oğul Can, A. Aydin Alatan

Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding image.

Image Retrieval Metric Learning +1

Blind Deinterleaving of Signals in Time Series with Self-attention Based Soft Min-cost Flow Learning

no code implementations • 24 Oct 2020 • Oğul Can, Yeti Z. Gürbüz, Berkin Yıldırım, A. Aydin Alatan

We propose an end-to-end learning approach to address deinterleaving of patterns in time series, in particular, radar signals.

Clustering Time Series +1