scholarly journals HQA‐Trans: An end‐to‐end high‐quality‐awareness image translation framework for unsupervised cross‐domain pedestrian detection

2021 ◽  
Author(s):  
Gelin Shen ◽  
Yang Yu ◽  
Zhi‐Ri Tang ◽  
Haoqiang Chen ◽  
Zongtan Zhou
Keyword(s):  
Pedestrian Detection ◽  
High Quality ◽  
Cross Domain ◽  
Image Translation ◽  
End To End ◽  
Quality Awareness

scholarly journals Frequency-domain loss function for deep exposure correction of dark images

2021 ◽  
Author(s):  
Ojasvi Yadav ◽  
Koustav Ghosal ◽  
Sebastian Lutz ◽  
Aljosa Smolic
Keyword(s):  
Loss Function ◽  
Correct Choice ◽  
Frequency Space ◽  
Multi Scale ◽  
Quantitative Metrics ◽  
Image Translation ◽  
Domain Loss ◽  
In The Wild ◽  
End To End ◽  
Classical Image

AbstractWe address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct choice of thresholds and frequency estimates. On the other hand, traditional deep networks are trained end to end in the RGB space by formulating this task as an image translation problem. However, that is done without any explicit constraints on the inherent noise of the dark images and thus produces noisy and blurry outputs. To this end, we propose a DCT/FFT-based multi-scale loss function, which when combined with traditional losses, trains a network to translate the important features for visually pleasing output. Our loss function is end to end differentiable, scale-agnostic and generic; i.e., it can be applied to both RAW and JPEG images in most existing frameworks without additional overhead. Using this loss function, we report significant improvements over the state of the art using quantitative metrics and subjective tests.

Cross-domain object detection using unsupervised image translation

2021 ◽  
pp. 116334
Author(s):  
Vinicius F. Arruda ◽  
Rodrigo F. Berriel ◽  
Thiago M. Paixão ◽  
Claudine Badue ◽  
Alberto F. De Souza ◽  
...  
Keyword(s):  
Object Detection ◽  
Cross Domain ◽  
Image Translation

Exploring Effective Speech Representation via ASR for High-Quality End-to-End Multispeaker TTS

2021 ◽  
pp. 110-118
Author(s):  
Dawei Liu ◽  
Longbiao Wang ◽  
Sheng Li ◽  
Haoyu Li ◽  
Chenchen Ding ◽  
...  
Keyword(s):  
High Quality ◽  
Speech Representation ◽  
End To End

scholarly journals End-to-End Visual Domain Adaptation Network for Cross-Domain 3D CPS Data Retrieval

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 118630-118638 ◽  
Author(s):  
An-An Liu ◽  
Shu Xiang ◽  
Wei-Zhi Nie ◽  
Dan Song
Keyword(s):  
Domain Adaptation ◽  
Data Retrieval ◽  
Cross Domain ◽  
End To End ◽  
Visual Domain
Sign in / Sign up

Export Citation Format

Share Document