1 code implementation • 6 Sep 2023 • Ada Gorgun, Yeti Z. Gurbuz, A. Aydin Alatan
Albeit useful especially in the penultimate layer and beyond, its action on student's feature transform is rather implicit, limiting its practice in the intermediate layers.
1 code implementation • ICCV 2023 • Yeti Z. Gurbuz, Ozan Sener, A. Aydin Alatan
GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively learning to ignore nuisance information, and ii) learning the weights corresponding to the importance of each entity.
no code implementations • 14 Jul 2023 • Yeti Z. Gurbuz, A. Aydin Alatan
Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features.
no code implementations • 3 Oct 2022 • Ada Gorgun, Yeti Z. Gurbuz, A. Aydin Alatan
Convolution blocks serve as local feature extractors and are the key to success of the neural networks.
1 code implementation • 19 Sep 2022 • Yeti Z. Gurbuz, Ogul 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 space.