Learning sequentially diversified representations for fine-grained categorization
作者：
Highlights：
• We present Sequentially Diversified Networks (SDNs) for fine-grained visual categorization. SDNs is composed of multiple lightweight sub-networks to learn different scales of discriminative regions. On top of one shared backbone, this design avoids multiple backbones or forward passes thus maintaining efficiency.
• We introduce a diversified constraint function that explicitly promotes feature diversity among branches while preserving class discrimination.
• SDNs reports state-of-the-art performance on three challenging datasets, including CUB-200-2011, Stanford Cars and FGVC-Aircraft.
摘要
•We present Sequentially Diversified Networks (SDNs) for fine-grained visual categorization. SDNs is composed of multiple lightweight sub-networks to learn different scales of discriminative regions. On top of one shared backbone, this design avoids multiple backbones or forward passes thus maintaining efficiency.•We introduce a diversified constraint function that explicitly promotes feature diversity among branches while preserving class discrimination.•SDNs reports state-of-the-art performance on three challenging datasets, including CUB-200-2011, Stanford Cars and FGVC-Aircraft.
论文关键词：Fine-grained visual categorization,Convolutional neural networks,Diversity learning,Object recognition
论文评审过程：Received 11 January 2021, Revised 29 July 2021, Accepted 31 July 2021, Available online 2 August 2021, Version of Record 8 August 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108219
