MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning

Sumanth, Chennupati; Sistu, Ganesh; Senthil, Yogamani; A, Rawashdeh Samir

doi:10.48550/arxiv.1904.08492

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This, in fact, offers scalability for adding new tasks at a minimal computation complexity. [Chennupati et al, 2019b] provided a detailed overview on negligible incremental computational complexity while increasing number of joint tasks solved by a multi-task network. On the other hand, using pre-trained encoders (say ResNet [He et al, 2016]) as a common encoder stage in multi-task networks reduces training time and alleviates the daunting requirements of massive data to optimize.…”

Section: Proposed Multi-task Architecturementioning

confidence: 99%

FisheyeMultiNet: Real-time Multi-task Learning Architecture for Surround-view Automated Parking System

Maddu,

Doherty,

Sistu

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

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 the design and implementation of an automated parking system from the perspective of camera based deep learning algorithms. We provide a holistic overview of an industrial system covering the embedded system, use cases and the deep learning architecture. We demonstrate a real-time multi-task deep learning network called FisheyeMultiNet, which detects all the necessary objects for parking on a low-power embedded system. FisheyeMultiNet runs at 15 fps for 4 cameras and it has three tasks namely object detection, semantic segmentation and soiling detection. To encourage further research, we release a partial dataset of 5,000 images containing semantic segmentation and bounding box detection ground truth via WoodScape project .

show abstract

Section: Proposed Multi-task Architecturementioning

confidence: 99%