Learning sequentially diversified representations for fine-grained categorization

Lianbo Zhang, Shaoli Huang, Wei Liu

Abstract: 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.