• Welcome to my Github page. I am a Ph.D at Inha University in South Korea.
  My research areas are machine learning, deep learning, and especially the light-weighting the convolutional neural networks such as knowledge distillation and filter pruning.
  You can find my curriculum vitaehere.

• Tensorflow (1.x and 2.x): Professional
• Pytorch: Upper intermediate
• JAX: Upper intermediate

• Google developers experts from May 2022
• Leader of deep learning paper study group:link
• Major contributor of the implementation project forPutting NeRF on a Dietin 🤗HuggingFace X GoogleAI Flax/JAX Community Week Event (won the 2nd price! 😆)
• Have served as a reviewer for CVPR, ICCV, ECCV, and so on.

• "Fast Filter Pruning via Coarse-to-Fine Neural Architecture Search and Contrastive Knowledge Transfer" on IEEE TNNLS (2023) [paper]
• "Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning" on ECCV2022 [paper] [code]
• "Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network" on AAAI2021 [paper] [code]
• "Knowledge Transfer via Decomposing Essential Information in Convolutional Neural Networks" on IEEE TNNLS (2020) [paper] [TF1 code,TF2 code]
• "Filter Pruning and Re-Initialization via Latent Space Clustering" on IEEE Access (2020) [paper]
• "Transformation of Non-Euclidean Space to Euclidean Space for Efficient Learning of Singular Vectors" on IEEE Access (2020) [paper]
• "Graph-based Knowledge Distillation by Multi-head Attention Network." on BMVC2019 oral [paper] [code]
• "Self-supervised Knowledge Distillation Using Singular Value Decomposition" on ECCV2018 [paper] [TF1 code,TF2 code]

• "CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization" on IEEE Access (2022) [paper] [code]
• "Balanced knowledge distillation for one-stage object detector" on Neurocomputing (2022) [paper]
• "Vision Transformer for Small-Size Datasets" on arxiv preprint [paper] [code]
• "Contextual Gradient Scaling for Few-Shot Learning" on WACV2022 [paper] [code]
• "Zero-Shot Knowledge Distillation Using Label-Free Adversarial Perturbation With Taylor Approximation" on IEEE Access (2021) [paper] [code]
• "Channel Pruning Via Gradient Of Mutual Information For Light-Weight Convolutional Neural Networks" on ICIP 2020 [paper]
• "Real-time purchase behavior recognition system based on deep learning-based object detection and tracking for an unmanned product cabinet" on ESWA (2020) [paper]
• "Metric-Based Regularization and Temporal Ensemble for Multi-Task Learning using Heterogeneous Unsupervised Tasks" on ICCVW2019 [paper]
• "MUNet: macro unit-based convolutional neural network for mobile devices" on CVPRW2018 [paper]

• Google scholar

PinnedLoading

1. KD_methods_with_TFKD_methods_with_TFPublic

   Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)

   Python 264 61

2. Knowledge_distillation_via_TF2.0Knowledge_distillation_via_TF2.0Public

   The codes for recent knowledge distillation algorithms and benchmark results via TF2.0 low-level API

   Python 109 31

3. codestella/putting-nerf-on-a-dietcodestella/putting-nerf-on-a-dietPublic

   Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis Implementation

   Python 268 19

4. Zero-shot_Knowledge_DistillationZero-shot_Knowledge_DistillationPublic

   Zero-Shot Knowledge Distillation in Deep Networks in ICML2019

   Python 48 9

5. SSKD_SVDSSKD_SVDPublic

   Python 50 10

6. EKGEKGPublic

   Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

   Python 18 1