Search Results for author: Shubhika Garg

Found 5 papers, 3 papers with code

Cross Modal Distillation for Flood Extent Mapping

no code implementations16 Feb 2023 Shubhika Garg, Ben Feinstein, Shahar Timnat, Vishal Batchu, Gideon Dror, Adi Gerzi Rosenthal, Varun Gulshan

Unlike the conventional self distillation setup, we propose a cross modal distillation framework that transfers supervision from a teacher trained on richer modality (multi-spectral images) to a student model trained on SAR imagery.

Knowledge Distillation

MSN: Efficient Online Mask Selection Network for Video Instance Segmentation

1 code implementation19 Jun 2021 Vidit Goel, Jiachen Li, Shubhika Garg, Harsh Maheshwari, Humphrey Shi

Our method improves the masks from segmentation and propagation branches in an online manner using the Mask Selection Network (MSN) hence limiting the noise accumulation during mask tracking.

Instance Segmentation Segmentation +4

Mask Selection and Propagation for Unsupervised Video Object Segmentation

1 code implementation5 Jan 2021 Shubhika Garg, Vidit Goel

We efficiently handle problems present in existing methods such as drift while temporal propagation, tracking and addition of new objects.

Segmentation Semantic Segmentation +2

MonoLayout: Amodal scene layout from a single image

3 code implementations19 Feb 2020 Kaustubh Mani, Swapnil Daga, Shubhika Garg, N. Sai Shankar, Krishna Murthy Jatavallabhula, K. Madhava Krishna

We dub this problem amodal scene layout estimation, which involves "hallucinating" scene layout for even parts of the world that are occluded in the image.

Amodal Layout Estimation Sensor Fusion

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