most citedX-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation

10 citations · 22 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV2022

X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation

Shubhankar Borse, Marvin Klingner, Varun Ravi Kumar +4

Bird's-eye-view (BEV) grid is a common representation for the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras on…

cs.CV2022

Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation

Shubhankar Borse, Hyojin Park, Hong Cai +3

This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extrac…

cs.CV20217 cited

HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation

Shubhankar Borse, Hong Cai, Yizhe Zhang +1

While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation…

cs.CV202110 cited

X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation

Hong Cai, Janarbek Matai, Shubhankar Borse +3

In this paper, we propose a novel method, X-Distill, to improve the self-supervised training of monocular depth via cross-task knowledge distillation from semantic segmentation to…

cs.CV2021

Perceptual Consistency in Video Segmentation

Yizhe Zhang, Shubhankar Borse, Hong Cai +4

In this paper, we present a novel perceptual consistency perspective on video semantic segmentation, which can capture both temporal consistency and pixel-wise correctness. Given t…

cs.CV20215 cited

AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation

Yizhe Zhang, Shubhankar Borse, Hong Cai +1

In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy. Existing methods rely either on optical flow regular…