activity
20202024
most citedGeneralized Sum Pooling for Metric Learning

1 citations · 3 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV20241 cited

IG-SLAM: Instant Gaussian SLAM

F. Aykut Sarikamis, A. Aydin Alatan

3D Gaussian Splatting has recently shown promising results as an alternative scene representation in SLAM systems to neural implicit representations. However, current methods eithe…

cs.CV20241 cited

XoFTR: Cross-modal Feature Matching Transformer

Önder Tuzcuoğlu, Aybora Köksal, Buğra Sofu +2

We introduce, XoFTR, a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images. Unlike visible images, TIR images are less suscep…

cs.CV2023

Knowledge Distillation Layer that Lets the Student Decide

Ada Gorgun, Yeti Z. Gurbuz, A. Aydin Alatan

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher).…

cs.CV20231 cited

Generalized Sum Pooling for Metric Learning

Yeti Z. Gurbuz, Ozan Sener, A. Aydın Alatan

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 a…

cs.LG2023

Generalizable Embeddings with Cross-batch Metric Learning

Yeti Z. Gurbuz, A. Aydin Alatan

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as…

eess.IV2023

MAEVI: Motion Aware Event-Based Video Frame Interpolation

Ahmet Akman, Onur Selim Kılıç, A. Aydın Alatan

Utilization of event-based cameras is expected to improve the visual quality of video frame interpolation solutions. We introduce a learning-based method to exploit moving region b…