27 citations · 50 across the 9 of their papers we have counts for
10 papers
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
Shao-Yuan Lo, Poojan Oza, Sumanth Chennupati +2
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target da…
Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation
Sumanth Chennupati, Mohammad Mahdi Kamani, Zhongwei Cheng +1
Knowledge Distillation is becoming one of the primary trends among neural network compression algorithms to improve the generalization performance of a smaller student model with g…
Learning Panoptic Segmentation from Instance Contours
Sumanth Chennupati, Venkatraman Narayanan, Ganesh Sistu +2
Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmenta…
Adaptive Hierarchical Decomposition of Large Deep Networks
Sumanth Chennupati, Sai Nooka, Shagan Sah +1
Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep le…
FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System
Pullarao Maddu, Wayne Doherty, Ganesh Sistu +7
Automated Parking is a low speed manoeuvring scenario which is quite unstructured and complex, requiring full 360° near-field sensing around the vehicle. In this paper, we discuss…
WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving
Senthil Yogamani, Ciaran Hughes, Jonathan Horgan +14
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence…
MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning
Sumanth Chennupati, Ganesh Sistu, Senthil Yogamani +1
Multi-task learning is commonly used in autonomous driving for solving various visual perception tasks. It offers significant benefits in terms of both performance and computationa…
NeurAll: Towards a Unified Visual Perception Model for Automated Driving
Ganesh Sistu, Isabelle Leang, Sumanth Chennupati +4
Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SL…
AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
Sumanth Chennupati, Ganesh Sistu, Senthil Yogamani +1
Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the…
Multi-stream CNN based Video Semantic Segmentation for Automated Driving
Ganesh Sistu, Sumanth Chennupati, Senthil Yogamani
Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm mo…