Related papers: ADFQ-ViT: Activation-Distribution-Friendly Post-Tr…

Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…

The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the…

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. However, their practical deployment is hindered by substantial…

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

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…

In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the…

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment…

Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs). However, ViT models are often computation-intensive for efficient deployment on…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Diffusion transformers (DiTs) combine transformer architectures with diffusion models. However, their computational complexity imposes significant limitations on real-time applications and sustainability of AI systems. In this study, we aim…

Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, which hinders…

Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique…

Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in…

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…

Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation. In comparison to convolutional…

Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers…

In computer vision, Single Image Super-Resolution (SISR) is still a difficult problem. We present ViT-SR, a new technique to improve the performance of a Vision Transformer (ViT) employing a two-stage training strategy. In our method, the…