The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. It is hypothesized that the well known tendency of standard classifier training to overfit to popular classes can be exploited for effective transfer learning. Rather than eliminating this overfitting, e.g. by adopting popular class-balanced sampling methods, the learning algorithm should instead leverage this overfitting to transfer geometric information from popular to low-shot classes. A new classifier architecture, GistNet, is proposed to support this goal, using constellations of classifier parameters to encode the class geometry. A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes. This enables better generalization for few-shot classes without the need for the manual specification of class weights, or even the explicit grouping of classes into different types. Experiments on two popular long-tailed recognition datasets show that GistNet outperforms existing solutions to this problem.
翻译:长期的认知问题,即每类实例数量高度不平衡的问题,得到了考虑。假设可以利用标准分类培训高于流行类的众所周知的趋势来有效地转移学习。学习算法不是消除这种过度,例如采用流行类平衡的抽样方法,而是利用这种超配,将流行类中的几何信息转移到低发类中。提出了一个新的分类结构,即GistNet,以支持这一目标,使用分类参数的星座来编码等级几何。然后为Geometric结构传输(GIST)提出一种新的学习算法,采用将损失功能相结合的办法,将分类平衡和随机抽样抽样结合起来,以保证在过度适应流行类中限于几何参数的同时,利用这种算法将等级的几何测量从流行类转到少发类中。这样可以更好地概括少数发类,而不需要对等级重量进行手工说明,甚至将班级明确组合成不同类型。两个受欢迎的长尾识别数据集的实验显示Gistmag 超越了现有解决方案。