Udit Sharma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Udit Sharma has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Savakis
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA
1 shared publication - Bruno Artacho
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA
1 shared publication
Latest Publications
- Open Access
GourmetNet: Food Segmentation Using Multi-Scale Waterfall Features with Spatial and Channel Attention
We propose GourmetNet, a single-pass, end-to-end trainable network for food segmentation that achieves state-of-the-art performance. Food segmentation is an important problem as the first step for nutrition monitoring, food volume and calorie estimation. Our novel architecture incorporates both channel attention and spatial attention information in an expanded multi-scale feature representation using our advanced Waterfall Atrous Spatial Pooling module. GourmetNet refines the feature extraction process by merging features from multiple levels of the backbone through the two attention modules. The refined features are processed with the advanced multi-scale waterfall module that combines the benefits of cascade filtering and pyramid representations without requiring a separate decoder or post-processing. Our experiments on two food datasets show that GourmetNet significantly outperforms existing current state-of-the-art methods.
Open AccessGourmetNet: Food Segmentation Using Multi-Scale Waterfall Features with Spatial and Channel Attention
We propose GourmetNet, a single-pass, end-to-end trainable network for food segmentation that achieves state-of-the-art performance. Food segmentation is an important problem as the first step for nutrition monitoring, food volume and calorie estimation. Our novel architecture incorporates both channel attention and spatial attention information in an expanded multi-scale feature representation using our advanced Waterfall Atrous Spatial Pooling module. GourmetNet refines the feature extraction process by merging features from multiple levels of the backbone through the two attention modules. The refined features are processed with the advanced multi-scale waterfall module that combines the benefits of cascade filtering and pyramid representations without requiring a separate decoder or post-processing. Our experiments on two food datasets show that GourmetNet significantly outperforms existing current state-of-the-art methods.