Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the
original data, but generates the fake sample via a generator (G) by learning from full …

Learning to synthesize data has emerged as a promising direction in zero-shot quantization
(ZSQ), which represents neural networks by low-bit integer without accessing any of the real …

Continual learning is an emerging research challenge in machine learning that addresses
the problem where models quickly fit the most recently trained-on data but suffer from …

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural
networks when the data for training full-precision models are inaccessible. In ZSQ, network …

Abstract Model quantization is considered as a promising method to greatly reduce the
resource requirements of deep neural networks. To deal with the performance drop induced …

Structured pruning and quantization are promising approaches for reducing the inference
time and memory footprint of neural networks. However, most existing methods require the …

Data-free quantization can potentially address data privacy and security concerns in model
compression and thus has been widely investigated. Recently, patch similarity aware data …

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without
accessing the real data, but generates the fake sample via a generator (G) by learning from …

We present CLAMP-ViT, a data-free post-training quantization method for vision
transformers (ViTs). We identify the limitations of recent techniques, notably their inability to …

Data-free quantization aims to achieve model quantization without accessing any authentic
sample. It is significant in an application-oriented context involving data privacy. Converting …