Fixed-point Inversion for Text-to-image diffusion models

1 code implementation • 19 Dec 2023 • Barak Meiri, Dvir Samuel, Nir Darshan, Gal Chechik, Shai Avidan, Rami Ben-Ari

Several applications of these models, including image editing interpolation, and semantic augmentation, require diffusion inversion.

Advancing Image Retrieval with Few-Shot Learning and Relevance Feedback

1 code implementation • 18 Dec 2023 • Boaz Lerner, Nir Darshan, Rami Ben-Ari

With such a massive growth in the number of images stored, efficient search in a database has become a crucial endeavor managed by image retrieval systems.

Binary Classification Classification +5

Watch Where You Head: A View-biased Domain Gap in Gait Recognition and Unsupervised Adaptation

no code implementations • 13 Jul 2023 • Gavriel Habib, Noa Barzilay, Or Shimshi, Rami Ben-Ari, Nir Darshan

Unsupervised Domain Adaptation (UDA) tries to adapt a model, pre-trained in a supervised manner on a source domain, to an unlabelled target domain.

Gait Recognition Unsupervised Domain Adaptation

Norm-guided latent space exploration for text-to-image generation

1 code implementation • NeurIPS 2023 • Dvir Samuel, Rami Ben-Ari, Nir Darshan, Haggai Maron, Gal Chechik

Text-to-image diffusion models show great potential in synthesizing a large variety of concepts in new compositions and scenarios.

Long-tail Learning Text-to-Image Generation

Chatting Makes Perfect: Chat-based Image Retrieval

1 code implementation • NeurIPS 2023 • Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski

These questions form a dialog with the user in order to retrieve the desired image from a large corpus.

Chat-based Image Retrieval Information Retrieval +1

Generating images of rare concepts using pre-trained diffusion models

1 code implementation • 27 Apr 2023 • Dvir Samuel, Rami Ben-Ari, Simon Raviv, Nir Darshan, Gal Chechik

We show that their limitation is partly due to the long-tail nature of their training data: web-crawled data sets are strongly unbalanced, causing models to under-represent concepts from the tail of the distribution.

Data Augmentation Text-to-Image Generation

Data Roaming and Quality Assessment for Composed Image Retrieval

1 code implementation • 16 Mar 2023 • Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski

To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones.

Composed Image Retrieval (CoIR) Retrieval