文章目录
往期文章链接目录
Introduction
When learning with long-tailed data, a common challenge is that instance-rich (or head) classes dominate the training procedure. The learned classification model tends to perform better on these classes, while performance is significantly worse for instance-scarce (or tail) classes (under-fitting).
The general scheme for long-tailed recognition is: classifiers are either learned jointly with the representations end-to-end, or via a two-stage approach where the classifier and the representation are jointly fine-tuned with variants of class-balanced sampling as a second stage.
In our work, we argue for decoupling representation and classification. We demonstrate that in a long-tailed scenario, this separation allows straightforward approaches to achieve high recognition performance, without the need for designing sampling strategies, balance-aware losses or adding memory modules.
Recent Directions
Recent studies’ directions on solving long-tailed recognition problem:
- Data distribution re-balancing. Re-sample the dataset to achieve a more balanced data distribution. These methods include over-sampling, down-sampling and class-balanced sampling.
- Class-balanced Losses. Assign different losses to different training samples for each class.
- Transfer learning from head- to tail classes. Transfer features learned from head classes with abundant training instances to under-represented tail classes. However it is usually a non-trivial task to design specific modules for feature transfer.
Sampling Strategies
For most sampling strategies presented below, the probability p j p_j pj of sampling a data point from class j j j is given by: p j = n j q ∑ i = 1 C n i q p_{j}=\frac{n_{j}^{q}}{\sum_{i=1}^{C} n_{i}^{q}} pj=∑i=1Cniqnjq where q ∈ [ 0 , 1 ] q \in[0,1] q∈[0,1], n j n_j nj denote the number of training sample for class j j j and C C C is the number of training classes. Different sampling strategies arise for different values of q q q and below we present strategies that correspond to q = 1 , q = 0 , q=1, q=0, q=1,q=0, and q = 1 / 2 q=1 / 2