Progressive Neural Architecture Search

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space... (read more)

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet PNASNet-5 Top 1 Accuracy 82.9% # 36
Top 5 Accuracy 96.2% # 25
Number of params 86.1M # 16

Methods used in the Paper