Publications | Prathmesh Bele

Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization

Thu, 04 Jan 2024 00:00:00 +0000

Developed SODG-Net, an end-to-end network outperforming benchmarks by 1-14% in open-domain settings. Proposed a style synthesis block generating diverse statistical features to effectively simulate novel domains. Formulated novel weight learning and margin objectives to establish distinct representations for open classes.

Node and Edge Embedding Learning for Static Obstacle Segmentation

Sun, 01 Jan 2023 00:00:00 +0000

Proposed a novel GNN architecture formulating free-space mapping as a scalable edge-prediction problem. Architected a dual-path Graph Attention Network to independently process node and edge features. Implemented class-aware edge retention via feature fusion, achieving parity with inflexible rule-based legacy systems.