Related papers: DocQT: Improving Document Forgery Localization Rob…

For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often…

Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent…

This study investigates the robustness of image classifiers to text-guided corruptions. We utilize diffusion models to edit images to different domains. Unlike other works that use synthetic or hand-picked data for benchmarking, we use…

Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…

Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods…

In machine learning, research has traditionally focused on model development, with relatively less attention paid to training data. As model architectures have matured and marginal gains from further refinements diminish, data quality has…

Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes.…

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Domain Adaptation (DA) is a highly relevant research topic when it comes to image classification with deep neural networks. Combining multiple source domains in a sophisticated way to optimize a classification model can improve the…

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an…

The advancement of imaging devices and countless images generated everyday pose an increasingly high demand on image denoising, which still remains a challenging task in terms of both effectiveness and efficiency. To improve denoising…

The rapid progress of subject-driven text-to-image synthesis, and in particular DreamBooth, has enabled a consent-free deepfake pipeline: an adversary needs only 4-8 publicly available face images to fine-tune a personalized diffusion model…

Code-documentation inconsistencies are common and undesirable: they can lead to developer misunderstandings and software defects. This paper introduces DocPrism, a multi-language, code-documentation inconsistency detection tool. DocPrism…

Many organizations rely on data from government and third-party sources, and those sources rarely follow the same data formatting. This introduces challenges in integrating data from multiple sources or aligning external sources with…

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…

Data filtering has become a powerful tool for improving model performance while reducing computational cost. However, as large language model compute budgets continue to grow, the limited data volume provided by heavily filtered and…

The quality of a face crop in an image is decided by many factors such as camera resolution, distance, and illumination condition. This makes the discrimination of face images with different qualities a challenging problem in realistic…

We present efficient realization of Householder Transform (HT) based QR factorization through algorithm-architecture co-design where we achieve performance improvement of 3-90x in-terms of Gflops/watt over state-of-the-art multicore,…

In the case that images are shared via social networking services (SNS) and cloud photo sharing services (CPSS), it is known that the JPEG images uploaded to the services are often re-compressed and resized by the providers. Because of such…