PEOPLE

Denis Gudovskiy Denis Gudovskiy

Denis Gudovskiy

M.Sc. in Computer Engineering
Panasonic AI Lab, Panasonic R&D Company of America

He specializes in deep learning-based algorithms for AI applications. His portfolio of research projects includes optimization of deep neural networks for edge AI devices, explainable AI tools, and automatic dataset management for computer vision applications.
In one of such projects he proposed and implemented a method of hardware-efficient neural network quantization and compression techniques for autonomous vehicles with stringent power and performance requirements. In the most recent work, Denis has demonstrated how data annotation costs could be significantly reduced with a use of advanced algorithms.His papers and demos are presented and published in top-tier machine learning and computer vision conferences such as NeurIPS, CVPR, ECCV, ICLR and ICASSP.
Within the explainable AI project, he has developed a tool to interpret and improve object detection results which contributes to Panasonic Automotive Company business. Denis sees corporate research as an important layer between moonshot academia projects and clearly-defined product development roadmaps in business units. His goal is to find and promote viable academia-grade opportunities at Panasonic within the exponentially growing landscape of AI applications.
In his free time, Denis enjoys riding motorcycles and mountaineering in Sierra Nevada.

*The department is where the interviewee belonged to at that time

Publications

  • The 41st International Conference on Machine Learning(ICML 2024)

    Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

    Anthony Chen, Huanrui Yang, Yulu Gan, Denis Gudovskiy, Zhen Dong, Haofan Wang, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
    arXiv: https://arxiv.org/abs/2312.09148

  • ICML '24 Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization

    Fisher-aware Quantization for DETR Detectors with Critical-category Objectives

    Huanrui Yang, Yafeng Huang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Yuan Du, Kurt Keutzer, Shanghang Zhang
    arXiv: https://arxiv.org/abs/2407.03442

  • The Conference on Uncertainty in Artificial Intelligence（UAI2024）

    ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding

    Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata
    arXiv: https://arxiv.org/abs/2406.00578

  • The 38th Annual AAAI Conference on Artificial Intelligence（AAAI 2024）

    Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation

    Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang
    arXiv: https://arxiv.org/abs/2312.16610

  • 39th Conference on Uncertainty in Artificial Intelligence (UAI2023)

    Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow

    Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata
    arXiv: https://arxiv.org/abs/2305.09610

  • European Conference on Computer Vision (ECCV) 2022

    MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer

    Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis Gudovskiy, Tomoyuki Okuno, Jianxin Li, Kurt Keutzer and Shanghang Zhang
    arXiv: https://arxiv.org/abs/2205.01643

  • Winter Conference on Applications of Computer Vision (WACV2022)

    CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows

    Denis Gudovskiy, Shun Ishizaka and Kazuki Kozuka
    Link: https://arxiv.org/abs/2107.12571

  • The 13th Asian Conference on Machine Learning (ACML2021)

    Contrastive Neural Processes for Self-Supervised Learning

    Konstantinos Kallidromitis, Denis Gudovskiy, Kazuki Kozuka, Iku Ohama and Luca Rigazio
    Link: http://www.acml-conf.org/2021/conference/accepted-papers/266/

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021

    AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

    Denis Gudovskiy,Luca Rigazio, Shun Ishizaka,Kazuki Kozuka, Sotaro Tsukizawa
    Link: https://arxiv.org/abs/2103.05863

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)

    Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision

    Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa
    Link: https://arxiv.org/abs/2003.00393

  • NeurIPS 2019 demo track

    Smart Home Appliances: Chat with Your Fridge

    Denis Gudovskiy, Gyuri Han, Takuya Yamaguchi, Sotaro Tsukizawa
    Link: https://arxiv.org/abs/1912.09589

  • ICLR The 2nd Learning from Limited Labeled Data (LLD) Workshop

    Explanation-Based Attention for Semi-Supervised Deep Active Learning

    Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa
    Link: https://openreview.net/forum?id=SyxKiVmedV

  • NeurIPS Workshop on Systems for ML and Open Source Software

    Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

    Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Yasunori Ishii, Sotaro Tsukizawa
    Link: https://arxiv.org/abs/1811.08011

  • ECCV 2nd International Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision (CEFRL 2018)

    DNN Feature Map Compression using Learned Representation over GF(2)

    Denis Gudovskiy, Alec Hodgkinson, Luca Rigazio
    Link: http://openaccess.thecvf.com/content_ECCVW_2018/papers/11132/Gudovskiy_DNN_Feature_Map_Compression_using_Learned_Representation_over_GF2_ECCVW_2018_paper.pdf