paper-with-me

홈 › Papers

Rethinking Performance Estimation in Neural Architecture Search

2020-05-20 · CVPR 2020 6 · Xiawu Zheng, Rongrong Ji, Qiang Wang, Qixiang Ye, Zhenguo Li, Yonghong Tian, Qi Tian

Neural architecture search (NAS) remains a challenging problem, which is attributed to the indispensable and time-consuming component of performance estimation (PE). In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space. Since searching an optimal BPE is extremely time-consuming as it requires to train a large number of networks for evaluation, we propose a Minimum Importance Pruning (MIP) approach. Given a dataset and a BPE search space, MIP estimates the importance of hyper-parameters using random forest and subsequently prunes the minimum one from the next iteration. In this way, MIP effectively prunes less important hyper-parameters to allocate more computational resource on more important ones, thus achieving an effective exploration. By combining BPE with various search algorithms including reinforcement learning, evolution algorithm, random search, and differentiable architecture search, we achieve 1, 000x of NAS speed up with a negligible performance drop comparing to the SOTA

📄 PDF Abstract BibTeX arXiv:2005.09917

Code (1)

zhengxiawu/rethinking_performance_estimation_in_NAS 공식 구현 pytorch

Tasks

Neural Architecture Search

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Rethinking on Multi-Stage Networks for Human Pose Estimation

2019-01-01 · Wenbo Li, Zhicheng Wang, Binyi Yin, Qixiang Peng 외

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good a…

Keypoint DetectionPose Estimation

MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation

2024-01-01 · CVPR 2024 1 · Haokai Zhu, Si-Yuan Cao, Jianxin Hu, Sitong Zuo 외

We propose Multiscale Correlation searching homography estimation Network namely MCNet an iterative deep homography estimation architecture. Different from previous approaches that achieve iterative refinement by cor…

Homography Estimation

Rethinking Encoder-Decoder Flow Through Shared Structures

2025-01-24 · Frederik Laboyrie, Mehmet Kerim Yucel, Albert Saa-Garriga

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We int…

DecoderDepth Estimation

Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

2018-12-14 · Martin Mundt, Sagnik Majumder, Tobias Weis, Visvanathan Ramesh

We characterize convolutional neural networks with respect to the relative amount of features per layer. Using a skew normal distribution as a parametrized framework, we investigate the common assumption of monotonously …

General Classificationimage-classificationImage Classification

Rethinking Internet Communication Through LLMs: How Close Are We?

2023-09-25 · Sifat Ut Taki, Spyridon Mastorakis

In this paper, we rethink the way that communication among users over the Internet, one of the fundamental outcomes of the Internet evolution, takes place. Instead of users communicating directly over the Internet, we ex…