13 citations · 45 across the 8 of their papers we have counts for
5 papers · 1 filter
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Dilin Wang, Chengyue Gong, Meng Li +2
Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles a…
SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
Can Peng, Kun Zhao, Sam Maksoud +2
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will…
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
Hsin-Pai Cheng, Feng Liang, Meng Li +5
Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neur…
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Chengyue Gong, Dilin Wang, Meng Li +2
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy aug…
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Dilin Wang, Meng Li, Chengyue Gong +1
Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, dec…