A Scale-Aware and Discriminative Feature Learning Network for Fine-Grained Rigid Object Recognition

This paper proposes the SD Net training framework: based on probability distribution functions, scale soft labels are constructed to guide learning, and discriminative feature extraction branches are designed for channel and spatial dimensions. On the FAIR1M-OR dataset, adding only a small number of parameters can improve the performance of the baseline model by about 4.6 percentage points.

Recommended citation:
Y. Gao, C. Deng, L. Chen and Z. Zhu (corresponding author), "A Scale-Aware and Discriminative Feature Learning Network for Fine-Grained Rigid Object Recognition," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 1695-1705, 2025, doi: 10.1109/JSTARS.2024.3484411.
Download Paper