Weakly Supervised Representation Learning with Coarse Labels
This addresses the challenge of expensive label collection in real-world applications like online shopping, offering a weakly supervised solution, though it appears incremental as it builds on existing representation learning methods.
The paper tackles the problem of learning fine-grained representations for a target task when only coarse-class labels are available, which is common in applications like visual search where task-specific labels are expensive. The result is a proposed algorithm with theoretical guarantees that significantly improves performance on real-world datasets.
With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark data sets. Many efforts have been devoted to studying the mechanism of deep learning. One important observation is that deep learning can learn the discriminative patterns from raw materials directly in a task-dependent manner. Therefore, the representations obtained by deep learning outperform hand-crafted features significantly. However, for some real-world applications, it is too expensive to collect the task-specific labels, such as visual search in online shopping. Compared to the limited availability of these task-specific labels, their coarse-class labels are much more affordable, but representations learned from them can be suboptimal for the target task. To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available. More importantly, we provide a theoretical guarantee for this. Extensive experiments on real-world data sets demonstrate that the proposed method can significantly improve the performance of learned representations on the target task, when only coarse-class information is available for training. Code is available at \url{https://github.com/idstcv/CoIns}.