Fast Neural Architecture Search for Lightweight Dense Prediction Networks

03/03/2022
by   Lam Huynh, et al.
6

We present LDP, a lightweight dense prediction neural architecture search (NAS) framework. Starting from a pre-defined generic backbone, LDP applies the novel Assisted Tabu Search for efficient architecture exploration. LDP is fast and suitable for various dense estimation problems, unlike previous NAS methods that are either computational demanding or deployed only for a single subtask. The performance of LPD is evaluated on monocular depth estimation, semantic segmentation, and image super-resolution tasks on diverse datasets, including NYU-Depth-v2, KITTI, Cityscapes, COCO-stuff, DIV2K, Set5, Set14, BSD100, Urban100. Experiments show that the proposed framework yields consistent improvements on all tested dense prediction tasks, while being 5%-315% more compact in terms of the number of model parameters than prior arts.

READ FULL TEXT

page 7

page 8

page 9

page 11

research
08/25/2021

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

This paper presents a novel neural architecture search method, called Li...
research
04/19/2021

Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS

The recent progress of deep convolutional neural networks has enabled gr...
research
05/09/2021

Lightweight Image Super-Resolution with Hierarchical and Differentiable Neural Architecture Search

Single Image Super-Resolution (SISR) tasks have achieved significant per...
research
04/19/2020

Superkernel Neural Architecture Search for Image Denoising

Recent advancements in Neural Architecture Search(NAS) resulted in findi...
research
07/28/2020

Efficient OCT Image Segmentation Using Neural Architecture Search

In this work, we propose a Neural Architecture Search (NAS) for retinal ...
research
10/04/2022

Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search

In this work, we propose a novel and scalable solution to address the ch...
research
03/02/2023

DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction

We present DejaVu, a novel framework which leverages conditional image r...

Please sign up or login with your details

Forgot password? Click here to reset