Yoshitomo Matsubara

torchdistill. A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

supervised-compression. [WACV 2022] "Supervised Compression for Resource-Constrained Edge Computing Systems"

head-network-distillation. [IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and [ACM MobiCom HotEdgeVideo 2019] "Distilled Split Deep Neural Networks for Edge-assisted Real-time Systems"

sc2-benchmark. [TMLR] "SC2 Benchmark: Supervised Compression for Split Computing"

hnd-ghnd-object-detectors. [ICPR 2020] "Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks" and [ACM MobiCom EMDL 2020] "Split Computing for Complex Object Detectors: Challenges and Preliminary Results"

uci-cs273a-project. Basic Support for Final Projects in UCI CS 273A: Machine Learning

bottlefit-split_computing. [IEEE WoWMoM 2022] "BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing"

split-beam. [ICDCS 2023] "SplitBeam: Effective and Efficient Beamforming in Wi-Fi Networks Through Split Computing"

ladon-multi-task-sc2. [WACV 2025] "A Multi-task Supervised Compression Model for Split Computing"

srbench. A living benchmark framework for symbolic regression

section-categorization. Automated Section Categorization in Scientific Papers

yoshitomo-matsubara.github.io. HTML