A. Aydin Alatan — accepted AI-conference papers

2023

Generalized Sum Pooling for Metric Learning

Yeti Z. Gürbüz, Ozan Sener, A. Aydin Alatan

ICCV 2023poster

A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the effectiveness of GAP is considering each feature vector as repres…

Cited by 5 PDF ↗code ↗Scholar ↗

2021

Blind Deinterleaving of Signals in Time Series with Self-Attention Based Soft Min-Cost Flow Learning

Ogul Can, Yeti Ziya Gürbüz, Berkin Yildirim, A. Aydin Alatan

ICASSP 2021accepted

We propose an end-to-end learning approach to address deinterleaving of patterns in time series, in particular, radar signals. We link signal clustering problem to min-cost flow as an equivalent problem once the proper costs exist. We formulate a bi-level optimization problem involving min-cost flow…

Cited by 0 Source ↗Scholar ↗