相关论文: Patch-wise Mixed-Precision Quantization of Vision …

The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for private inference using secure multi-party computation (MPC)…

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating…

Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-constrained mobile devices or even desktop GPUs. Recent…

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC…

Vision Transformers (ViTs) and their variants have become state-of-the-art in many computer vision tasks and are widely used as backbones in large-scale vision and vision-language foundation models. While substantial research has focused on…

Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance drop compared to…

Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs). Recent advances primarily target at crafting quantizers to deal with peculiar activations…

Vision Transformers (ViTs) have achieved remarkable success in standard RGB image processing tasks. However, applying ViTs to multi-channel imaging (MCI) data, e.g., for medical and remote sensing applications, remains a challenge. In…

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…

Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative value metric, patch similarity, to generate data from…

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Networks (CNNs) have…

Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the…

Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In…

Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference. However, existing neural network architectures, including Vision Transformers (ViTs),…

Data-Free Quantization (DFQ) enables the quantization of Vision Transformers (ViTs) without requiring access to data, allowing for the deployment of ViTs on devices with limited resources. In DFQ, the quantization model must be calibrated…

Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transformers (ViTs) have been…

Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for…

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for…

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,…