Abstract: Real-time object detection on edge devices operates under tight computational, memory, and power budgets. Prior work typically treats model compression and hardware acceleration ...
DEIMv2 is an evolution of the DEIM framework while leveraging the rich features from DINOv3. Our method is designed with various model sizes, from an ultra-light version up to S, M, L, and X, to be ...
Stop deploying AI models with inflated performance scores. Sleuth detects hidden bias caused by tweaking hyperparameters, prompts, or datasets during evaluation—breaking circular reasoning in AI ...
Abstract: The performance of existing object detection algorithms significantly degrades when applied to low-resolution infrared (IR) images captured by unmanned aerial vehicles (UAVs), which suffers ...
The U.S. Naval Research Laboratory (NRL) launched a remote sensing experiment to sharpen artificial intelligence (AI) applications in hyperspectral imaging across the Department of the Navy and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results