Search Results for author:
Found 7 papers, 5 papers with code
SparseNet: A Sparse DenseNet for Image Classification
Deep neural networks have made remarkable progresses on various computer vision tasks.
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report
Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices.
Scaling transition from momentum stochastic gradient descent to plain stochastic gradient descent
The momentum stochastic gradient descent uses the accumulated gradient as the updated direction of the current parameters, which has a faster training speed.
A decreasing scaling transition scheme from Adam to SGD
Adaptive gradient algorithm (AdaGrad) and its variants, such as RMSProp, Adam, AMSGrad, etc, have been widely used in deep learning.
Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning
To relieve the burden of labor-intensive labeling, deep unsupervised SOD methods have been proposed to exploit noisy labels generated by handcrafted saliency methods.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment
Considering the limited quantity of labeled video data, we propose a semi-supervised fire detection model called FireMatch, which is based on consistency regularization and adversarial distribution alignment.
