CLIP model is an Efficient Continual Learner

1 code implementation • 6 Oct 2022 • Vishal Thengane, Salman Khan, Munawar Hayat, Fahad Khan

In this work, we show that a frozen CLIP (Contrastive Language-Image Pretraining) model offers astounding continual learning performance without any fine-tuning (zero-shot evaluation).

Continual Learning Incremental Learning +1

Strong Gravitational Lensing Parameter Estimation with Vision Transformer

1 code implementation • 9 Oct 2022 • Kuan-Wei Huang, Geoff Chih-Fan Chen, Po-Wen Chang, Sheng-Chieh Lin, Chia-Jung Hsu, Vishal Thengane, Joshua Yao-Yu Lin

Quantifying the parameters and corresponding uncertainties of hundreds of strongly lensed quasar systems holds the key to resolving one of the most important scientific questions: the Hubble constant ($H_{0}$) tension.

Gradient Correlation Subspace Learning against Catastrophic Forgetting

1 code implementation • 4 Mar 2024 • Tammuz Dubnov, Vishal Thengane

Efficient continual learning techniques have been a topic of significant research over the last few years.

Continual Learning