Welcome to Deeplite's blog! A place to discover helpful content on computer vision and perception model optimization, inference acceleration, tinyML and other topics related to achieving smaller, faster and more cost-efficient AI to run on edge devices and in the cloud.
This blog is a summary of the research paper Sah, Sudakar, et al. "ActNAS: Generating Efficient YOLO Models using Activation NAS", accepted at the NeurIPS 2024 FITML Workshop.
In the ever-evolving field of computer vision, the YOLO family of models has set benchmarks for real-time object...
This blog is a summary of the research paper Sah, Sudakar, et al. "Token Pruning using a Lightweight Background Aware Vision Transformer", accepted at the NeurIPS 2024 FITML Workshop.
In the realm of computer vision, Vision Transformers (ViTs) have emerged as a powerful tool, outperforming...
This blog is a summary of the research paper Sah, Sudakar, et al. "MCUBench A Benchmark of Tiny Object Detectors on MCUs." Proceedings of the IEEE/CVF European Conference on Computer Vision 2024, accepted at the ECCV 2024 CADL Workshop. You can find the CADL Workshop presentation here.
In the...
The rapid advancements in AI have revolutionized various industries, promising enhanced productivity and innovation. However, deploying AI models on AI processors presents significant challenges, impacting the sales of these processors. This blog explores these challenges and how semiconductor...
Exciting news! We are thrilled to unveil the latest hardware benchmarks for the cutting-edge Raspberry Pi 5 featuring the Arm Cortex A76 processor @ 2.4GHz. Dive into the comparison between the Raspberry Pi 5 and 4 models, as well as other edge hardware platforms, using the powerful YOLOBench tool.
This blog is a summary of a Medium article that you can find here.
We are excited to release YOLOBench, a latency-accuracy benchmark of over 900 YOLO-based object detectors for embedded use cases. Accepted at the ICCV 2023 RCV workshop, you can read the full paper on arXiv.
Check out the...
The proliferation of edge devices has unlocked unprecedented opportunities for deep learning model deployment in computer vision applications. However, these complex models require considerable power, memory and compute resources that are typically not available on edge platforms. Ultra low-bit...