no code implementations • 18 Apr 2024 • Azad Singh, Vandan Gorade, Deepak Mishra
In response to these constraints, we introduce a novel SSL framework OPTiML, employing optimal transport (OT), to capture the dense semantic invariance and fine-grained details, thereby enhancing the overall effectiveness of SSL in medical image representation learning.
no code implementations • 18 Mar 2024 • Azad Singh, Vandan Gorade, Deepak Mishra
The performance enhancements we observe across various downstream tasks highlight the significance of the proposed approach in enhancing the utility of chest X-ray embeddings for precision medical diagnosis and comprehensive image analysis.
no code implementations • 24 Apr 2022 • Vandan Gorade, Azad Singh, Deepak Mishra
To tackle these problems, we propose a non-contrastive self-supervised learning approach efficiently captures low and high-frequency time-varying features in a cost-effective manner.
no code implementations • 1 Jan 2021 • Mayank Kumar Kundalwal, Azad Singh, Deepak Mishra
We propose to model this problem in indirect supervision framework, where we assume that the gold standard data is missing, however, a variable dependent on it is available and the dependency of the observed variable is stated by the considered downstream DNN.