Modern computer vision systems have superhuman accuracy when it comes to image recognition and analysis, but they don’t really understand what they see. At IBM Research, we’re designing AI systems with the ability to see the world like we do.
TiM is a novel approach for computer vision models similar to chain-of-thought in language models. Empirical evidence demonstrates that TiM tuning can enhance the model performance beyond normal fine-tuning.
Within this tutorial, we will delve into the algorithmic foundations of MU methods, including techniques such as localization-informed unlearning, unlearning-focused finetuning, and vision model-specific optimizers. We will provide a comprehensive and clear overview of the diverse range of applications for MU in CV.
A new way to generate synthetic data for pretraining computer vision models IBM's Task2Sim churns out synthetic images tailored for specific AI tasks to reduce the need for real data. From chatbots to spellcheckers, modern AI was built on real data.
Computer Vision Our research interests include learning with limited labels, cross-domain, self-supervised and multi-modal learning, and modern model architectures. We focus on innovative state-of-the-art research that makes a difference. Read more about Computer Vision at IBM Research - Israel
The last time generative AI loomed this large, the breakthroughs were in computer vision. Selfies transformed into Renaissance-style portraits and prematurely aged faces filled social media feeds. Five years later, it’s the leap forward in natural language processing, and the ability of large language models to riff on just about any theme, that has seized the popular imagination. And it’s ...
Inspecto is an industry-research SaaS where this technology is prototyped and validated in collaboration with clients, before graduating into IBM products. Inspecto combines the use of LVMs, with advanced computer vision tools to enable engineers to perform complex inspection tasks.
Visual Prompting is a paradigm shift in the field of computer vision: being able to build an accurate segmentation model in just a few seconds of work was unthinkable a few years ago. The benefit of this technology lies in its application in technical domains, where the available data is usually limited, and new models are needed on a daily basis.
Earth observation (EO) differs fundamentally from other computer vision (CV) problems. Unlike tasks such as reading credit card characters or detecting people in images, RGB (red, green, blue) data alone cannot meet the complex needs of agriculture, environmental monitoring, or disaster response. That's why we've focused on innovations that address the unique demands of EO data, advancing the ...
