Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• BlankSkip achieves up to 24% average throughput improvement compared to a static MobileNet-SSD detector on a nano-drone platform.result 95%
• BlankSkip's early-exit mechanism is based on a lightweight binary classifier that identifies frames with no objects of interest.method 90%
• The BlankSkip architecture increases the total parameter count by only 1.1–3.0% over the original 4.67M parameter SSD model.technical 90%
• Deploying object detection on nano-drones is complicated by extremely tight constraints of approximately 10 MiB memory and a 1 W power budget.technical 95%
• The system is trained end-to-end with a composite loss function that includes a weighted binary cross-entropy term for the early-exit branch.method 90%
• Higher early-exit branch weight w_0 penalizes false positives (non-empty images classified as empty), prioritizing detection completeness.technical 85%
• The method was deployed and evaluated on a real-world nano-drone platform, the Bitcraze Crazyflie 2.1 with a GAP8 SoC.result 90%
• All DNNs were quantized to 8-bit integer format using Quantization-Aware Training (QAT) for deployment on the GAP8 SoC.method 85%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card