Related papers: Q-ViT: Fully Differentiable Quantization for Visio…

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of…

Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a widespread model compression technique, existing post-training…

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training quantization (PTQ) reduces model size and speeds up inference, it often degrades performance,…

Transformer-based architectures have revolutionized the landscape of deep learning. In computer vision domain, Vision Transformer demonstrates remarkable performance on par with or even surpassing that of convolutional neural networks.…

Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self attention blocks. However, unlike Convolutional…

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…

Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN), offering a potential solution to the deployment challenges faced by Vision Transformers (ViTs)…

Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. In this work, we present ViT-Linearizer, a cross-architecture…

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…

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

Vision transformers have shown remarkable performance in vision tasks, but enabling them for accessible and real-time use is still challenging. Quantization reduces memory and inference costs at the risk of performance loss. Strides have…

Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT…

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Pruning, a traditional model…