Previous Next

Welcome to Visual Computing Lab at IISc

Welcome to the Visual Computing Lab (VCL) at the Indian Institute of Science, Bangalore. We are a part of Department of Computational and Data Sciences (CDS). The group was established in June 2017 with Anirban Chakraborty as the convenor.

In Visual Computing Lab, we are interested in developing novel computer vision and machine learning algorithms to solve visual analytics problems arising from diverse real-world applications. Majority of our ongoing research projects can be categorized into one of the following three areas

1. Data-efficient & privacy-preserving deep learning (zero-shot/few-shot knowledge distillation, continual learning, source-free/unsupervised domain adaptation, data-free adversarial defense etc. Additionally, we are interested in both the theoretical foundations and practical implementations of federated learning under distribution shifts - with a focus on generalization, fairness, domain adaptation and efficient fine-tuning of foundational models.)
2. Cross-modal computer vision and generative models (text-based image retrieval, sketch-guided localization, scene-graph generation, visual question answering, video to audio synthesis etc.)
3. Perceiving humans and their actions (robust and scalable person-reidentification, video anomaly detection, human gait and pose analysis etc.)