Multi-layer Representation Learning for Robust OOD Image Classification

被引:2
作者
Ballas, Aristotelis [1 ]
Diou, Christos [1 ]
机构
[1] Harokopio Univ, Dept Informat & Telemat, Athens, Greece
来源
PROCEEDINGS OF THE 12TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE, SETN 2022 | 2022年
关键词
deep learning; domain generalization; out of distribution; image classification;
D O I
10.1145/3549737.3549780
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past few years. In order to utilize such models in real-world scenarios and applications, they must be able to provide trustworthy predictions on unseen data. In this paper, we argue that extracting features from a CNN's intermediate layers can assist in the model's final prediction. Specifically, we adapt the Hypercolumns method to a ResNet-18 and find a significant increase in the model's accuracy, when evaluating on the NICO dataset.
引用
收藏
页数:4
相关论文
共 23 条
[1]  
Arjovsky M, 2020, Arxiv, DOI arXiv:1907.02893
[2]  
Bai HY, 2020, Arxiv, DOI arXiv:2012.09382
[3]  
Blanchard Gilles, 2011, P 24 INT C NEUR INF
[4]  
Bochkovskiy A, 2020, Arxiv, DOI arXiv:2004.10934
[5]   Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns [J].
Hariharan, Bharath ;
Arbelaez, Pablo ;
Girshick, Ross ;
Malik, Jitendra .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (04) :627-639
[6]  
Hariharan B, 2015, PROC CVPR IEEE, P447, DOI 10.1109/CVPR.2015.7298642
[7]   Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1026-1034
[8]   Towards Non-IID image classification: A dataset and baselines [J].
He, Yue ;
Shen, Zheyan ;
Cui, Peng .
PATTERN RECOGNITION, 2021, 110
[9]   RECEPTIVE FIELDS, BINOCULAR INTERACTION AND FUNCTIONAL ARCHITECTURE IN CATS VISUAL CORTEX [J].
HUBEL, DH ;
WIESEL, TN .
JOURNAL OF PHYSIOLOGY-LONDON, 1962, 160 (01) :106-&
[10]   A survey of deep meta-learning [J].
Huisman, Mike ;
van Rijn, Jan N. ;
Plaat, Aske .
ARTIFICIAL INTELLIGENCE REVIEW, 2021, 54 (06) :4483-4541