PV-NAS: Practical Neural Architecture Search for Video Recognition

11/02/2020
by   Zihao Wang, et al.
0

Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability. Deep neural networks for video tasks is highly customized and the design of such networks requires domain experts and costly trial and error tests. Recent advance in network architecture search has boosted the image recognition performance in a large margin. However, automatic designing of video recognition network is less explored. In this study, we propose a practical solution, namely Practical Video Neural Architecture Search (PV-NAS).Our PV-NAS can efficiently search across tremendous large scale of architectures in a novel spatial-temporal network search space using the gradient based search methods. To avoid sticking into sub-optimal solutions, we propose a novel learning rate scheduler to encourage sufficient network diversity of the searched models. Extensive empirical evaluations show that the proposed PV-NAS achieves state-of-the-art performance with much fewer computational resources. 1) Within light-weight models, our PV-NAS-L achieves 78.7 and Something-Something V2, which are better than previous state-of-the-art methods (i.e., TSM) with a large margin (4.6 respectively), and 2) among median-weight models, our PV-NAS-M achieves the best performance (also a new record)in the Something-Something V2 dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2020

Neural Architecture Search of SPD Manifold Networks

In this paper, we propose a new neural architecture search (NAS) problem...
research
05/23/2022

FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?

The existence of a plethora of language models makes the problem of sele...
research
01/23/2022

Neural Architecture Search for Spiking Neural Networks

Spiking Neural Networks (SNNs) have gained huge attention as a potential...
research
05/21/2021

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

Human pose estimation has achieved significant progress in recent years....
research
01/24/2022

Neural Architecture Searching for Facial Attributes-based Depression Recognition

Recent studies show that depression can be partially reflected from huma...
research
05/13/2019

ISBNet: Instance-aware Selective Branching Network

Recent years have witnessed growing interests in designing efficient neu...
research
08/30/2021

Searching for Two-Stream Models in Multivariate Space for Video Recognition

Conventional video models rely on a single stream to capture the complex...

Please sign up or login with your details

Forgot password? Click here to reset