Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

This paper aims at addressing the problem of substantial performance degradation at
extremely low computational cost (eg 5M FLOPs on ImageNet classification). We found that …

Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …

Multi-task learning commonly encounters competition for resources among tasks,
specifically when model capacity is limited. This challenge motivates models which allow …

In many web applications, deep learning-based CTR prediction models (deep CTR models
for short) are widely adopted. Traditional deep CTR models learn patterns in a static …

Semantic segmentation arises as the backbone of many vision systems, spanning from self-
driving cars and robot navigation to augmented reality and teleconferencing. Frequently …

In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have
shown remarkable performance outperforming traditional geometric methods. Yet, all …

Recently there has been a lot of progress in reducing the computation of deep models at
inference time. These methods can reduce both the computational needs and power usage …

Feature pyramid network (FPN) is a critical component in modern object detection
frameworks. The performance gain in most of the existing FPN variants is mainly attributed to …