Fused One-vs-All Mid-Level Features for Fine-Grained Visual Categorization

As an emerging research topic, fine-grained visual catego-rization has been attracting growing attentions in recent years. Due to the large inter-class similarity and intra-class variance, recognizing objects in fine-grained domains is ex-tremely challenging, and sometimes even humans can not recognize them accurately. Traditional bag-of-words model could obtain desirable results for basic-level category classi-fication by weak alignment using spatial pyramid matching model, but may easily fail in fine-grained domains since the discriminative features are not only subtle but also extreme-ly localized. The fine differences often get swamped by those irrelevant features, and it is virtually impossible to distin-guish them. To address the problems above, we propose a new frame