DocumentCode :
3748577
Title :
Multi-scale Recognition with DAG-CNNs
Author :
Songfan Yang;Deva Ramanan
Author_Institution :
Coll. of Electron. &
fYear :
2015
Firstpage :
1215
Lastpage :
1223
Abstract :
We explore multi-scale convolutional neural nets (CNNs) for image classification. Contemporary approaches extract features from a single output layer. By extracting features from multiple layers, one can simultaneously reason about high, mid, and low-level features during classification. The resulting multi-scale architecture can itself be seen as a feed-forward model that is structured as a directed acyclic graph (DAG-CNNs). We use DAG-CNNs to learn a set of multi-scale features that can be effectively shared between coarse and fine-grained classification tasks. While fine-tuning such models helps performance, we show that even "off-the-self" multi-scale features perform quite well. We present extensive analysis and demonstrate state-of-the-art classification performance on three standard scene benchmarks (SUN397, MIT67, and Scene15). In terms of the heavily benchmarked MIT67 and Scene15 datasets, our results reduce the lowest previously-reported error by 23.9% and 9.5%, respectively.
Keywords :
"Feature extraction","Computer architecture","Computational modeling","Benchmark testing","Training","Image recognition","Neural networks"
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2015 IEEE International Conference on
Electronic_ISBN :
2380-7504
Type :
conf
DOI :
10.1109/ICCV.2015.144
Filename :
7410501
Link To Document :
بازگشت