# Fast Neural Architecture Search for Lightweight Dense Prediction Networks

Source: [Fast Neural Architecture Search for Lightweight Dense Prediction Networks](<https://www.sota2.com/research/paper/68fa6bf21e209131cea311aa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:59:56.170Z

Authors: Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila

Published: 2022-03-03T20:17:10.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.01994>)

[PDF](<https://arxiv.org/pdf/2203.01994.pdf>)