相关论文: Patch Similarity Aware Data-Free Quantization for …

Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory usage. This motivates the…

How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and…

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

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 scale that is quadratic to the number of tokens, $N$. This is…

Since the introduction of Vision Transformer (ViT), patchification has long been regarded as a de facto image tokenization approach for plain visual architectures. By compressing the spatial size of images, this approach can effectively…

Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining. Nevertheless, current PTQ methods for Vision Transformers…

Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video…

Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit…

The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the application domains to various vision tasks. While achieving high…

Model quantization is a promising approach to compress deep neural networks and accelerate inference, making it possible to be deployed on mobile and edge devices. To retain the high performance of full-precision models, most existing…

Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output remains sensitive to small spatial shifts in the input, i.e.,…

The majority of quantization methods have been proposed to reduce the model size of Vision Transformers, yet most of them have overlooked the quantization of non-linear operations. Only a few works have addressed quantization for non-linear…

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the…