Discriminative Feature
Discriminative feature learning aims to identify and extract the most informative features from data, enabling accurate classification and improved model performance across various tasks. Current research focuses on enhancing feature extraction in challenging scenarios, such as fine-grained recognition and open-set recognition, often employing attention mechanisms, multi-modal fusion, and generative models within deep learning architectures. These advancements are crucial for improving the accuracy and robustness of machine learning models in diverse applications, including image recognition, video analysis, and biomedical image analysis. The development of more effective discriminative feature learning techniques is driving progress in numerous fields by enabling more accurate and reliable automated systems.
Papers
Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Quan Feng, Jiayu Yao, Zhison Pan, Guojun Zhou
Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments
Tal Golan, Wenxuan Guo, Heiko H. Schütt, Nikolaus Kriegeskorte