Attribute Adaptive Margin Softmax Loss using Privileged Information
This work addresses the problem of enhancing recognition accuracy in computer vision by leveraging additional data during training, though it is incremental as it builds on existing margin-based and privileged information methods.
The paper tackles improving recognition tasks by using privileged information (soft biometric traits) only available during training to adjust adaptive margins between classes, resulting in more discriminative feature spaces and superior performance on face recognition and person re-identification across five datasets.
We present a novel framework to exploit privileged information for recognition which is provided only during the training phase. Here, we focus on recognition task where images are provided as the main view and soft biometric traits (attributes) are provided as the privileged data (only available during training phase). We demonstrate that more discriminative feature space can be learned by enforcing a deep network to adjust adaptive margins between classes utilizing attributes. This tight constraint also effectively reduces the class imbalance inherent in the local data neighborhood, thus carving more balanced class boundaries locally and using feature space more efficiently. Extensive experiments are performed on five different datasets and the results show the superiority of our method compared to the state-of-the-art models in both tasks of face recognition and person re-identification.