CB-DistillGrad: Class-Balanced Distillation and Gradient Conflict Resolution for Low Power Edge AI Applications

Deploying deep neural networks on edge devices such as embedded GPUs and FPGAs remains challenging due to high computational cost, memory footprint, and sensitivity to class imbalance. Existing compression techniques, including knowledge distillation, often overlook hardware constraints and minority-class performance, leading to suboptimal real-world deployment. This article introduces CB-DistillGrad, a unified hardware-aware distillation framework that jointly optimizes accuracy, model compactness, and deployment efficiency. The proposed system integrates: (1) a lightweight student architecture built with depthwise separable convolutions, squeeze-and-excitation attention, progressive dropout, and hardware-friendly Hard Swish activation; (2) aCB-Distill Lossthat couples class-balanced focal loss with reweighted Kullback–Leibler divergence to mitigate teacher bias and improve minority-class accuracy; and (3)gradient conflict resolutionvia PCGrad to stabilize optimization under multi-objective supervision. The resulting student network achieves 87.11% overall accuracy on the RSCD road-surface dataset using only 130K parameters (0.52 MB at FP32), a 96.8% reduction compared to the 4.1M-parameter teacher. On the NVIDIA GPU, inference occurs at 1.05 ms/image (949 FPS) with 72Wpower, 2.15× faster than the teacher. On the NVIDIA Jetson AGX Orin, inference occurs at 11.70 ms/image (85 FPS) with 7.36 W power, achieving 2.8× speedup and 4.5× energy reduction. On the Xilinx ZCU104 FPGA, inference occurs at 62.19 ms/image (16 FPS) with 4.42Wpower, demonstrating a 27× energy reduction compared to GPU execution. These results demonstrate a practical framework for training and deploying compact, class-balanced, and hardware-optimized deep learning models on resource-constrained platforms.