Related papers: Fonts-2-Handwriting: A Seed-Augment-Train framewor…

Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in the sense that they can be trained only on fully labeled…

One of the most pressing problems in the automated analysis of historical documents is the availability of annotated training data. The problem is that labeling samples is a time-consuming task because it requires human expertise and thus,…

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…

In this work, we explore massive pre-training on synthetic word images for enhancing the performance on four benchmark downstream handwriting analysis tasks. To this end, we build a large synthetic dataset of word images rendered in several…

Although deep salient object detection (SOD) has achieved remarkable progress, deep SOD models are extremely data-hungry, requiring large-scale pixel-wise annotations to deliver such promising results. In this paper, we propose a novel yet…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

We introduce Seed-to-Seed Translation (StS), a novel approach for Image-to-Image Translation using diffusion models (DMs), aimed at translations that require close adherence to the structure of the source image. In contrast to existing…

Generating synthetic images is an art which emulates the natural process of image generation in a closest possible manner. In this work, we exploit such a framework for data generation in handwritten domain. We render synthetic data using…

In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set…

Text-to-image generation aims at generating realistic images which are semantically consistent with the given text. Previous works mainly adopt the multi-stage architecture by stacking generator-discriminator pairs to engage multiple…

The paper presents a novel technique called "Structural Crossing-Over" to synthesize qualified data for training machine learning-based handwriting recognition. The proposed technique can provide a greater variety of patterns of training…

This work provides a solution to the challenge of small amounts of training data in Non-Destructive Ultrasonic Testing for composite components. It was demonstrated that direct simulation alone is ineffective at producing training data that…

Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new annotations of synthetic images, which forces practitioners to…

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set…

We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT). The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more…

Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task. In recent years, AttnGAN based on the Attention mechanism to guide GAN training…

In recent years, semantic segmentation has become a pivotal tool in processing and interpreting satellite imagery. Yet, a prevalent limitation of supervised learning techniques remains the need for extensive manual annotations by experts.…

Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

We present the largest publicly available synthetic OCR benchmark dataset for Indic languages. The collection contains a total of 90k images and their ground truth for 23 Indic languages. OCR model validation in Indic languages require a…