Robust Image Ordinal Regression with Controllable Image Generation
This addresses robustness issues in ordinal regression for computer vision applications, though it appears incremental as it builds on existing encoders and models.
The paper tackles class imbalance and category overlap in image ordinal regression by proposing CIG, a controllable image generation framework that creates extra training samples biased toward minority categories. Results show CIG improves performance when integrated with existing models, with more significant gains for minority categories.
Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framework called CIG based on controllable image generation to directly tackle these two issues. Our main idea is to generate extra training samples with specific labels near category boundaries, and the sample generation is biased toward the less-represented categories. To achieve controllable image generation, we seek to separate structural and categorical information of images based on structural similarity, categorical similarity, and reconstruction constraints. We evaluate the effectiveness of our new CIG approach in three different image ordinal regression scenarios. The results demonstrate that CIG can be flexibly integrated with off-the-shelf image encoders or ordinal regression models to achieve improvement, and further, the improvement is more significant for minority categories.