Hey, I'm Jonathan Kahana

I am a Computer Science PhD student at the Hebrew University of Jerusalem, under the supervision of Dr. Yedid Hoshen. The focus of my research is representation learning, specifically disentangled representation learning and concept based representations.

Email Scholar Resume Github Twitter

Publications

Improving Zero-Shot Models with Label Distribution Priors

Arxiv Preprint
Jonathan Kahana, Niv Cohen Yedid Hoshen

We propose a new approach for zero-shot labeling of large image datasets, CLIPPR (CLIP with Priors), which adapts zero-shot models for regression and classification on unlabelled datasets. Our method does not use any annotated images. Instead, we assume a prior over the label distribution in the dataset. We then train an adapter network on top of CLIP under two competing objectives: i) minimal change of predictions from the original CLIP model ii) minimal distance between predicted and prior distribution of labels. Our method is effective and presents a significant improvement over the original model.

Project Page arXiv Code

An image illustrating DCoDR representations.

A Contrastive Objective for Learning Disentangled Representations

ECCV 2022
Jonathan Kahana, Yedid Hoshen

We present a new approach for domain-disentanglement, proposing a new domain-wise contrastive objective for ensuring invariant representations. In an extensive evaluation, our method convincingly outperforms the state-of-the-art in terms of representation invariance, representation informativeness, and training speed. Furthermore, we find that in some cases our method can achieve excellent results even without the reconstruction constraint, leading to a much faster and resource efficient training.

arXiv Code

An image showing anomalies and psuedo-anomalies from Red PANDA

Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors

Arxiv Preprint
Niv Cohen, Jonathan Kahana, Yedid Hoshen

We present a new anomaly detection method that allows operators to exclude an attribute from being considered as relevant for anomaly detection. Our approach then learns representations which do not contain information over the nuisance attributes. Anomaly scoring is performed using a density-based approach. Importantly, our approach does not require specifying the attributes that are relevant for detecting anomalies, which is typically impossible in anomaly detection, but only attributes to ignore. An empirical investigation is presented verifying the effectiveness of our approach.

arXiv