The mixture proportions of pretraining data domains (e.g., Wikipedia, bo...
We present a method to formulate algorithm discovery as program search, ...
The increasing complexity and scale of machine learning (ML) has led to ...
A variety of real-world applications rely on far future information to m...
Deep learning (DL) has proven to be a highly effective approach for
deve...
In this paper, we consider a different data format for images: vector
gr...
The energy consumption of deep learning models is increasing at a
breath...
Neural architectures and hardware accelerators have been two driving for...
Zero-shot learning (ZSL) aims to classify images of an unseen class only...
We present Supervision by Registration and Triangulation (SRT), an
unsup...
Neural networks are sensitive to hyper-parameter and architecture choice...
Neural architecture search (NAS) has attracted a lot of attention and ha...
Neural Architecture Search (NAS) has achieved significant progress in pu...
Neural architecture search (NAS) has achieved breakthrough success in a ...
Neural architecture search (NAS) aims to automate the search procedure o...
Conventional neural architecture search (NAS) approaches are based on
re...
Facial landmark detection aims to localize the anatomically defined poin...
Network pruning reduces the computation costs of an over-parameterized
n...
Prevailing deep convolutional neural networks (CNNs) for person
re-IDent...
This paper proposed a Progressive Soft Filter Pruning method (PSFP) to p...
This paper proposed a Soft Filter Pruning (SFP) method to accelerate the...
In this paper, we present supervision-by-registration, an unsupervised
a...
Recent advances in facial landmark detection achieve success by learning...
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) be...
This paper focuses on regularizing the training of the convolutional neu...
In this paper, we study object detection using a large pool of unlabeled...
In this paper, we present a novel and general network structure towards
...