139 citations · 934 across the 48 of their papers we have counts for
8 papers · 1 filter
Improving Auto-Augment via Augmentation-Wise Weight Sharing
Keyu Tian, Chen Lin, Ming Sun +3
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search i…
Adaptive Gradient Method with Resilience and Momentum
Jie Liu, Chen Lin, Chuming Li +4
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some r…
Towards Unified INT8 Training for Convolutional Neural Network
Feng Zhu, Ruihao Gong, Fengwei Yu +5
Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can furth…
Learning to Auto Weight: Entirely Data-driven and Highly Efficient Weighting Framework
Zhenmao Li, Yichao Wu, Ken Chen +4
Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborio…
Knowledge Distillation via Route Constrained Optimization
Xiao Jin, Baoyun Peng, Yichao Wu +5
Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured a…
Synaptic Strength For Convolutional Neural Network
Chen Lin, Zhao Zhong, Wei Wu +1
Convolutional Neural Networks(CNNs) are both computation and memory intensive which hindered their deployment in mobile devices. Inspired by the relevant concept in neural science…