.png){kind=icon}
Return
Learning sequentially diversified representations for fine-grained categorization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108219.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Learning representation carrying rich local information is essential for recognizing fine-grained objects. Existing methods to this task resort to multi-stage frameworks to capture fine-grained information. However, they usually require multiple forward passes of the backbone network, resulting in efficiency deterioration. In this paper, we propose Sequentially Diversified Networks (SDNs) that enrich representation by promoting their diversity while maintaining the extraction efficiency. Specifically, we construct multiple lightweight sub-networks to model mutually different scales of discriminative patterns. The design of these sub-networks follows the sequentially diversified constraint, encouraging them to be varied in spatial attention. By inserting these sub-networks into a single backbone network, SDNs enable information interaction among local regions of the fine-grained image. In this way, SDNs jointly promote diversity in terms of scale and spatial attention in the one-stage pipeline, thereby facilitating the learning of diversified representation efficiently. We evaluate our proposed method on three challenging datasets, namely CUB-200-2011, Stanford-Cars, and FGVC-Aircraft. Experiments demonstrate its effectiveness in learning diversified information. Moreover, our method achieves state-of-the-art performance, only requiring a single forward pass of the backbone network, which reduces inference time noticeably. (c) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Fine-grained visual categorization
Convolutional neural networks
Diversity learning
Object recognition
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveSaliency for fine-grained object recognition in domains with scarce training data.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveDeep cascaded cross-modal correlation learning for fine-grained sketch-based image retrievalPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveAttention-shift based deep neural network for fine-grained visual categorizationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveShareSaveA novel localized and second order feature coding network for image recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveLG-CNN: From local parts to global discrimination for fine-grained recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more