Hoang Anh Dung — accepted AI-conference papers

2024

MetaAug: Meta-Data Augmentation for Post-Training Quantization

Cuong Van Pham*, Hoang Anh Dung, Cuong Cao Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro +1

ECCV 2024poster

"Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large training set is not available. However, it often leads…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Sharpness-Aware Data Generation for Zero-shot Quantization

Hoang Anh Dung, Cuong Pham, Trung Le, Jianfei Cai, Thanh-Toan Do

ICML 2024poster

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing the full-precision model. While it is well-known that deep n…

Cited by 0 Source ↗PDF ↗Scholar ↗