Understanding the patterns of misclassified ImageNet images is particularly important, as it could guide us to design deep neural networks (DNN) that generalize better. However, the richness of ImageNet imposes difficulties for researchers to visually find any useful patterns of misclassification. Here, to help find these patterns, we propose "Superclassing ImageNet dataset". It is a subset of ImageNet which consists of 10 superclasses, each containing 7-116 related subclasses (e.g., 52 bird types, 116 dog types). By training neural networks on this dataset, we found that: (i) Misclassifications are rarely across superclasses, but mainly among subclasses within a superclass. (ii) Ensemble networks trained each only on subclasses of a given superclass perform better than the same network trained on all subclasses of all superclasses. Hence, we propose a two-stage Super-Sub framework, and demonstrate that: (i) The framework improves overall classification performance by 3.3%, by first inferring a superclass using a generalist superclass-level network, and then using a specialized network for final subclass-level classification. (ii) Although the total parameter storage cost increases to a factor N+1 for N superclasses compared to using a single network, with finetuning, delta and quantization aware training techniques this can be reduced to 0.2N+1. Another advantage of this efficient implementation is that the memory cost on the GPU during inference is equivalent to using only one network. The reason is we initiate each subclass-level network through addition of small parameter variations (deltas) to the superclass-level network. (iii) Finally, our framework promises to be more scalable and generalizable than the common alternative of simply scaling up a vanilla network in size, since very large networks often suffer from overfitting and gradient vanishing.
翻译:理解错误分类图像网络图像的图案特别重要, 因为它可以指导我们设计更普通化的深神经网络( DNN) 。 但是, 图像网络的丰富性使得研究人员难以视觉发现任何有用的分类错误模式。 在这里, 为了帮助找到这些模式, 我们提议“ 超高级图像网络数据集 ” 。 它是图像网络的一个子集, 由10个超级类组成, 每个类包含7-116个相关子类( 例如, 52 鸟类, 116 狗类 ) 。 通过在这个数据集上培训神经网络( DNNNNNNNNNNNNNNNNNMT 网络 ), 我们发现:(i) 错误分类很少跨越超级类, 主要是在超级类中, 而在超级类中, 仅仅训练每个子类的子类, 比所有超级类的所有子类的网络更好。 因此, 我们提议了一个两阶段超级子类框架, 并且证明:(i) 框架可以改进整个分类的绩效到3.3%, 首先推断一个超级类, 使用一个超级的超级的超级级的超级级 高级的网络, Ndel- develop com 网络, 然后使用一个专门的网络升级的升级的网络升级的网络, 然后使用一个专门的网络, 升级的网络, 升级的升级的网络, 升级的升级的网络, 级, 升级的升级的升级的网络, 升级的升级的升级的升级的升级的升级的网络, 级, 级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级级, 级级级级级, 升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级的升级