Despite the impressive progress in neural network architecture design, improving the performance of the existing state-of-the-art models has become increasingly challenging …
X He, K Zhao, X Chu - Knowledge-based systems, 2021 - Elsevier
Deep learning (DL) techniques have obtained remarkable achievements on various tasks, such as image recognition, object detection, and language modeling. However, building a …
Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly …
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a …
W Chen, X Gong, Z Wang - arXiv preprint arXiv:2102.11535, 2021 - arxiv.org
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive …
P Ye, B Li, Y Li, T Chen, J Fan… - proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Neural Architecture Search (NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural network automatically. Among …
In the past decade, advances in deep learning have resulted in breakthroughs in a variety of areas, including computer vision, natural language understanding, speech recognition, and …
Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets …
Object tracking has achieved significant progress over the past few years. However, state-of- the-art trackers become increasingly heavy and expensive, which limits their deployments in …