Suchergebnisse - "Optimization methods; Recognition: detection"

SpotTune: Transfer Learning Through Adaptive Fine-Tuning von Guo, Yunhui, Shi, Honghui, Kumar, Abhishek, Grauman, Kristen, Rosing, Tajana, Feris, Rogerio

“… Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting …”
Volltext

Learning Not to Learn: Training Deep Neural Networks With Biased Data von Kim, Byungju, Kim, Hyunwoo, Kim, Kyungsu, Kim, Sungjin, Kim, Junmo

“… We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network …”
Volltext

PPDL: Predicate Probability Distribution based Loss for Unbiased Scene Graph Generation von Li, Wei, Zhang, Haiwei, Bai, Qijie, Zhao, Guoqing, Jiang, Ning, Yuan, Xiaojie

“… Scene Graph Generation (SGG) has attracted more and more attention from visual researchers in recent years, since Scene Graph (SG) is valuable in many …”
Volltext

Deeply-Supervised Knowledge Synergy von Sun, Dawei, Yao, Anbang, Zhou, Aojun, Zhao, Hao

“… Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme …”
Volltext

P2SGrad: Refined Gradients for Optimizing Deep Face Models von Zhang, Xiao, Zhao, Rui, Yan, Junjie, Gao, Mengya, Qiao, Yu, Wang, Xiaogang, Li, Hongsheng

“… Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive …”
Volltext

A Local Block Coordinate Descent Algorithm for the CSC Model von Zisselman, Ev, Sulam, Jeremias, Elad, Michael

“… The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities. By providing a global, …”
Volltext

AME: Attention and Memory Enhancement in Hyper-Parameter Optimization von Xu, Nuo, Chang, Jianlong, Nie, Xing, Huo, Chunlei, Xiang, Shiming, Pan, Chunhong

“… Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation. To solve these two …”
Volltext