-
Chungnam National University
- Republic of Korea
- sangho0804.github.io
Stars
(KDD 2026) PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
Official Implementation of Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling (ICLR'25-Spotlight)
Tensorflow implementation of Swin Transformer model.
[SenSys'24] PieBridge: Fast and Parameter-Efficient On-Device Training via Proxy Networks
Scalable data pre processing and curation toolkit for LLMs
ultralytics / thop
Forked from Lyken17/pytorch-OpCounterProfile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.
A subjective learning guide for generative AI research
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
This is the official implementation of the paper "Instance-conditional Knowledge Distillation for Object Detection", based on MegEngine and Pytorch.
On-Device Training Under 256KB Memory [NeurIPS'22]
Code for paper "ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection" (MobiSys'23)
Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"
The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.
Light-Weight RefineNet for Real-Time Semantic Segmentation
Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Semantic Segmentation for Recycling Trash