Boaz Lerner — accepted AI-conference papers

2025

EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition

Issar Tzachor, Boaz Lerner, Matan Levy, Michael Green, Tal Berkovitz Shalev, Gavriel Habib +5

ICLR 2025poster

The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like DINOv2 for the VPR task. However, these models are often deeme…

Cited by 10 Source ↗PDF ↗Scholar ↗

2020

Inference Graphs for CNN Interpretation

Yael Konforti, Alon Shpigler, Boaz Lerner, Aharon Bar-Hillel

ECCV 2020poster

Convolutional neural networks (CNNs) have achieved superior accuracy in many visual related tasks. However, the inference process through intermediate layers is opaque, making it difficult to interpret such networks or develop trust in their operation. We propose to model the network hidden layers a…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗