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.

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

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

Distributional Robustness Loss for Long-tail Learning

no code implementations • ICCV 2021 • Dvir Samuel, Gal Chechik

The new robustness loss can be combined with various classifier balancing techniques and can be applied to representations at several layers of the deep model.

Long-tail Learning

From Generalized zero-shot learning to long-tail with class descriptors

1 code implementation • 5 Apr 2020 • Dvir Samuel, Yuval Atzmon, Gal Chechik

Real-world data is predominantly unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes.

Few-Shot Learning Generalized Zero-Shot Learning +1