Saptarshi Mitra

Ph.D. Researcher, EECS at UCI | Hardware Acceleration of ML

prof_pic_bw_compressed.JPG

66112 Verano Place

Irvine, CA 92617

Office: Engineering Hall, 308 5200

Irvine, CA 92697

Currently I am working as a Ph.D. researcher at UC Irvine with Prof. Hyoukjun Kwon. My research interests include domain-specific computer architectures, hardware acceleration of ML workloads, hardware aware machine learning. I am passionate about designing deep learning solutions to challenging problems and deploying them to low-power devices.

Previously. I worked as an Embedded AI Research Engineer at Deeplite in Toronto. There I primarily worked with compilers and runtimes to deploy Deep Learning vision models in low-power embedded devices. I have completed my Master of Science in Communication Engineering with a focus on hardware acceleration for inference at the Technical University of Munich under Prof. Walter Stechele. Earlier, I spent time with Intel working on Digital Design Verification and System Debugger tools validation.

Besides spending time in front of a screen or tweaking hardware, I am fond of hiking, biking and do occasional landscape photography. Having “well trained” taste buds I am picking up with culinary skills. Here is a link to my outdated website.

news

Jan 19, 2024 US Patent filed for Lookup Tables for Ultra Low-Bit Operations :sparkles:
Aug 25, 2023 DeepliteRT paper accepted at BMVC 2023! :sparkles:
Jul 26, 2023 YOLOBench paper accepted at the RCV workshop at ICCV 2023! [Code] :sparkles:
Apr 6, 2023 DeepGEMM paper accepted at the Efficient Computer Vision Workshop at CVPR 2023! :sparkles:
May 30, 2022 Moved to Toronto and joined as full-time Embedded AI Engineer in R&D at Deeplite :computer:
Feb 22, 2022 Accelerating and pruning CNNs for semantic segmentation on FPGA accepted at DAC 2022!

selected publications

  1. BMVC
    DeepliteRT: Computer Vision at the Edge
    Ashfaq, Saad, Hoffman, Alexander,  Mitra, Saptarshi, Sah, Sudhakar, AskariHemmat, MohammadHossein, and Saboori, Ehsan
    2023
  2. ICCVW
    YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems
    Lazarevich, Ivan, Grimaldi, Matteo, Kumar, Ravish,  Mitra, Saptarshi, Khan, Shahrukh, and Sah, Sudhakar
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops Oct 2023
  3. CVPRW
    DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures Using Lookup Tables
    Ganji, Darshan C., Ashfaq, Saad, Saboori, Ehsan, Sah, Sudhakar,  Mitra, Saptarshi, AskariHemmat, MohammadHossein, Hoffman, Alexander, Hassanien, Ahmed, and Léonardon, Mathieu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops Jun 2023
  4. DAC
    Accelerating and Pruning CNNs for Semantic Segmentation on FPGA
    Morı̀, Pierpaolo, Vemparala, Manoj-Rohit, Fasfous, Nael,  Mitra, SaptarshiSarkar, Sreetama, Frickenstein, Alexander, Frickenstein, Lukas, Helms, Domenik, Nagaraja, Naveen Shankar, Stechele, Walter, and Passerone, Claudio
    In Proceedings of the 59th ACM/IEEE Design Automation Conference Jun 2022