Publications & Patents

Research papers, conference publications, and patented innovations in machine learning, computer vision, and graph neural networks.

Conference Paper January 2024

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

Prathmesh Bele, Valay Bundele, Avigyan Bhattacharya, Ankit Jha, Gemma Roig, Biplab Banerjee

In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV'24)

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.

Patent January 2023

Node and Edge Embedding Learning for Static Obstacle Segmentation

Prathmesh Bele*, Apurva Kulkarni*, Hitul Desai, Amey Kavde, Dashrath Mali, Laxmikant Sahoo, et al.

Intellectual Property of India, Reference No. 202341087789

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.