Back to Search
Start Over
MSEC: Multi-Scale Erasure and Confusion for fine-grained image classification.
- Source :
-
Neurocomputing . Aug2021, Vol. 449, p1-14. 14p. - Publication Year :
- 2021
-
Abstract
- With the rapid development of deep learning, the performance of fine-grained image classification has experienced unprecedented improvement. However, for fine-grained image classification, quickly and effectively focusing on subtle discriminative details that make the sub-classes different from each other has always been challenging. In this paper, we propose a novel Multi-Scale Erasure and Confusion (MSEC) method to tackle the challenge of fine-grained image classification. Firstly, the input image is divided into several sub-regions, and the confidence scores of those sub-regions are calculated by the confidence function. The sub-regions with lower confidence scores are then erased by the Region Erasure Module (REM) and the erased image is confused once by the Multi-scale Region Confusion Module (Multi-scale RCM). Secondly, the sub-regions with higher confidence scores are divided and confused again by the Multi-scale RCM, and then generate an image with multi-scale information. Finally, features in the erased image and the "destructed" image are extracted by the backbone network, and the whole network is optimized by the multi-loss function to realize classification tasks. Extensive experiments on three standard fine-grained benchmark datasets, including Stanford Dogs, CUB-200-2011 and FGVC-Aircraft, show that MSEC can improve the accuracy of fine-grained image classification. [ABSTRACT FROM AUTHOR]
- Subjects :
- *DEEP learning
*CLASSIFICATION
Subjects
Details
- Language :
- English
- ISSN :
- 09252312
- Volume :
- 449
- Database :
- Academic Search Index
- Journal :
- Neurocomputing
- Publication Type :
- Academic Journal
- Accession number :
- 150291813
- Full Text :
- https://doi.org/10.1016/j.neucom.2021.03.114