Related papers: Semantic Alignment and Reinforcement for Data-Free…

Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant…

Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths,…

In computer vision, depth estimation is crucial for domains like robotics, autonomous vehicles, augmented reality, and virtual reality. Integrating semantics with depth enhances scene understanding through reciprocal information sharing.…

Performing unsupervised domain adaptation on resource-constrained edge devices is challenging. Existing research typically adopts architecture optimization (e.g., designing slimmable networks) but requires expensive training costs.…

While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably brittle when confronted with optical illusions. These failures are often attributed to…

Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training…

Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their heavy inference burden hinders real-world deployment. While Post-Training Quantization (PTQ)…

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly optimize over the…

Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted extensive attention in recent years. Currently, the majority of…

Data augmentation has been recently leveraged as an effective regularizer in various vision-language deep neural networks. However, in text-to-image synthesis (T2Isyn), current augmentation wisdom still suffers from the semantic mismatch…

In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. This is realized through two key designs: (1) multi-scale…

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…

Deep learning-based semantic communication has largely relied on analog or semi-digital transmission, which limits compatibility with modern digital communication infrastructures. Recent studies have employed vector quantization (VQ) to…

The scarcity of annotated surgical data poses a significant challenge for developing deep learning systems in computer-assisted interventions. While diffusion models can synthesize realistic images, they often suffer from data memorization,…

Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic…

Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from severe error accumulation, while generic joint models lack…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

With the rapid advancement of image generation techniques, robust forgery detection has become increasingly imperative to ensure the trustworthiness of digital media. Recent research indicates that the learned semantic concepts of…

Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic…