13 citations · 29 across the 6 of their papers we have counts for
6 papers
SymBa: Symmetric Backpropagation-Free Contrastive Learning with Forward-Forward Algorithm for Optimizing Convergence
Heung-Chang Lee, Jeonggeun Song
The paper proposes a new algorithm called SymBa that aims to achieve more biologically plausible learning than Back-Propagation (BP). The algorithm is based on the Forward-Forward…
X-ViT: High Performance Linear Vision Transformer without Softmax
Jeonggeun Song, Heung-Chang Lee
Vision transformers have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a sc…
Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning
Do-Guk Kim, Heung-Chang Lee
Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer…
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
Jongheon Jeong, Sejun Park, Minkyu Kim +3
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against -adversarial perturbations. Under the…
Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement
Do-Guk Kim, Heung-Chang Lee
Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT)…
Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
Heung-Chang Lee, Do-Guk Kim, Bohyung Han
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models fro…