Related papers: Data Factory with Minimal Human Effort Using VLMs

Generative techniques for image anonymization have great potential to generate datasets that protect the privacy of those depicted in the images, while achieving high data fidelity and utility. Existing methods have focused extensively on…

The availability of labeled image datasets has been shown critical for high-level image understanding, which continuously drives the progress of feature designing and models developing. However, constructing labeled image datasets is…

Nuclei segmentation is a fundamental but challenging task in the quantitative analysis of histopathology images. Although fully-supervised deep learning-based methods have made significant progress, a large number of labeled images are…

This paper demonstrates how to use generative models trained for image synthesis as tools for visual data mining. Our insight is that since contemporary generative models learn an accurate representation of their training data, we can use…

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates…

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale…

Fashionable image generation aims to synthesize images of diverse fashion prevalent around the globe, helping fashion designers in real-time visualization by giving them a basic customized structure of how a specific design preference would…

Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data…

Obtaining annotated table structure data for complex tables is a challenging task due to the inherent diversity and complexity of real-world document layouts. The scarcity of publicly available datasets with comprehensive annotations for…

This technical report outlines our method for generating a synthetic dataset for semantic segmentation using a latent diffusion model. Our approach eliminates the need for additional models specifically trained on segmentation data and is…

Text-to-image models have made significant strides, producing impressive results in generating images from textual descriptions. However, creating a scalable pipeline for deploying these models in production remains a challenge. Achieving…

The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited…

Recent advancements in language-guided diffusion models for image editing are often bottle-necked by cumbersome prompt engineering to precisely articulate desired changes. An intuitive alternative calls on guidance from in-the-wild image…

Synthetic data generation is an important application of machine learning in the field of medical imaging. While existing approaches have successfully applied fine-tuned diffusion models for synthesizing medical images, we explore potential…

Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture…

Existing latent diffusion models typically couple scale with content complexity, using more latent tokens to represent higher-resolution images or higher-frame rate videos. However, the latent capacity required to represent visual data…

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using…

Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock…