computer vision

We were thrilled to have Deeplite CEO and cofounder, Nick Romano present Deeplite's pitch at the Google for Startups Accelerator: Canada Demo Day!  The program, workshops and mentorship was second to none.  What a wonderful experience.  Thank you so much to Iran Karimian and Alice Kawka for...

Sudhakar Sah (Sud), cofounder atDeeplitepresented not one but two of our research papers at the NeurIPS FITML Workshop in Vancouver, Canada on December 14th:  

ActNAS: Generating Efficient YOLO Models using Activation NAS

Token Pruning using a Lightweight Background Aware Vision Transformer

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, Sudhakar, 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, Sudhakar, 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...

We are thrilled to announce that Deeplite has been selected to join the prestigious 2024 Google for Startups Accelerator: Canada cohort! This exciting opportunity marks a significant milestone in our journey to accelerate the adoption of AI processors for embedded devices by creating the best AI...

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...

Recently, Deeplite CEO Nick Romano sat down with CyberNews, a resource for cybersecurity news, tech analysis and product reviews, to discuss Deeplite, the AI industry and what he thinks is coming for the future of AI.

We were pleased to announce earlier this week that Deeplite was crowned as a Silver Stevie winner in the 2022 International Business Awards, in the Artificial Intelligence/Machine Learning Solution category. The team was thrilled to receive this honor and get recognition for Deeplite Neutrino and...

Deeplite’s AI optimization solutions honored with Silver Stevie® award

Here at Deeplite, we've been enjoying a number of opportunities to safely talk about the work we are doing, in person! Through a number of recent industry trade shows, we've been able to promote our solutions and how we are making AI accessible across a wide range of edge devices.