⚡ 本页包含 AI 生成的分析内容，仅供参考
本文提出了一款采用16nm工艺、支持双向特征金字塔网络（Bi-Directional FPN）的CNN处理器，峰值性能达5.7TOPS。该处理器针对高分辨率视频中的小目标检测进行了架构优化，解决了传统处理器在处理小目标时精度与效率不足的问题。
Kai-Feng Chang1, Yu-Ching Su1, Tsung-Han Hsieh1, Yu-Kuan Jian1, Wen-Ching Chen2, Nian-Shyang Chang2, Chun-Pin Lin2, Chi-Shi Chen2, Chao-Tsung Huang1 National Tsing Hua University, Hsinchu, Taiwan Taiwan Semiconductor Research Institute, Hsinchu, Taiwan 1 2 Object detection is vital in intelligent systems like autonomous vehicles, UAVs, VR/AR, and smart robots. Detecting small objects is particularly crucial and can be life-saving for ADAS, as it helps maintain awareness of distant objects to ensure safe following distances. As illustrated in Fig. 2.5.1, distant pedestrians may appear as less than one thousand pixels in a 2M-resolution image, making them hard to detect with low-resolution inputs and shallow networks as supported in prior works. EfficientDet-D3 [6] significantly improves detection precision of small objects by using a high-resolution 896×896 input with its deep 77-layer backbone and advanced multi-layer stacked bidirectional feature pyramid network (Bi-FPN).
Yu-Chun Ding1, Chia-Yu Chang1, Chun-Yeh Lin1, Hui-Yun Tsai1, Hao-Jiun Tu1,