Search Results for author: J. Ramanujam

Found 3 papers, 0 papers with code

Enhancing Weakly Supervised Semantic Segmentation with Multi-modal Foundation Models: An End-to-End Approach

no code implementations10 May 2024 Elham Ravanbakhsh, Cheng Niu, Yongqing Liang, J. Ramanujam, Xin Li

Weakly-Supervised Semantic Segmentation (WSSS) offers a cost-efficient workaround to extensive labeling in comparison to fully-supervised methods by using partial or incomplete labels.

Pseudo Label Segmentation +2

HPX Smart Executors

no code implementations5 Nov 2017 Zahra Khatami, Lukas Troska, Hartmut Kaiser, J. Ramanujam, Adrian Serio

Moreover, we advocate a novel method by introducing HPX smart executors for determining the execution policy, chunk size, and prefetching distance of an HPX loop to achieve higher possible performance by feeding static information captured during compilation and runtime-based dynamic information to our learning model.

Cannot find the paper you are looking for? You can Submit a new open access paper.