Arantxa Casanova from @element_ai presenting her work from milamontreal at #wad at #cvpr18

Arantxa Casanova from milamontreal presenting her work on iterative refinement of densely connected representation levels for semantic segmentation at #WiCV18 #CVPR18.

Check out our work on *Reinforced active learning for semantic segmentation* ICLR 2026 presented by Arantxa Casanova Thursday 13:00-15:00 and 16:00-18:00 EDT - Paper: arxiv.org/pdf/2002.06583… - Poster & slides: iclr.cc/virtual/poster… - Code:github.com/ArantxaCasanov…

We’ve built a new image generation model called Instance-Conditioned GAN. Unlike traditional GANs, IC-GANs can create high-quality images of entirely unfamiliar objects and scenes that aren’t part of the model’s training data. Code+ details: ai.facebook.com/blog/instance-…

A demo of Instance-Conditioned GAN by Arantxa Casanova et al at Facebook AI. It can generate images in a style of another image and can be conditioned by a class to alter the image. replicate.ai/arantxacasanov…

We are looking to hire FAIR research interns (current PhD students) in 2022. Previous works led by students: arxiv.org/abs/1812.06164, arxiv.org/abs/1902.03051, arxiv.org/abs/2007.03778, arxiv.org/abs/2109.05070, arxiv.org/abs/2110.13100. DM me or Michal Drozdzal with bio and CV.

I am looking for PhD students for a 2024 summer internship at Meta in Generative AI: metacareers.com/jobs/175996402… Specially relevant if interested in improving controllability and expressivity of image generative models, and want to work on challenging, domain-specific problems.