Related papers: Synthesizing Annotated Image and Video Data Using …

Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic…

Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in…

Artifact detectors have been shown to enhance the performance of image-generative models by serving as reward models during fine-tuning. These detectors enable the generative model to improve overall output fidelity and aesthetics. However,…

Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend…

Learning robust object detectors from only a handful of images is a critical challenge in industrial vision systems, where collecting high quality training data can take months. Synthetic data has emerged as a key solution for data…

Recently, advancements in vehicle-to-infrastructure communication technologies have elevated the significance of infrastructure-based roadside perception systems for cooperative driving. This paper delves into one of its most pivotal…

Person re-identification (re-ID) has gained more and more attention due to its widespread applications in intelligent video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…

Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training…

While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans,…

Synthesizing realistic medical images provides a feasible solution to the shortage of training data in deep learning based medical image recognition systems. However, the quality control of synthetic images for data augmentation purposes is…

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain…

High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require intensive investments and yield low-diversity scenarios. The…

Detecting and tracking objects is a crucial component of any autonomous navigation method. For the past decades, object detection has yielded promising results using neural networks on various datasets. While many methods focus on…

A central challenge in data visualization is to understand which data samples are required to generate an image of a data set in which the relevant information is encoded. In this work, we make a first step towards answering the question of…

Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometry from monocular images. Existing datasets are either real, with manually annotated 3D…

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which…

Traffic sign recognition is a well-researched problem in computer vision. However, the state of the art methods works only for frequent sign classes, which are well represented in training datasets. We consider the task of rare traffic sign…

Creating annotated datasets demands a substantial amount of manual effort. In this proof-of-concept work, we address this issue by proposing a novel image generation pipeline. The pipeline consists of three distinct generative adversarial…

In this paper, we are interested in addressing the problem of damage assessment for vehicles, such as cars. This task requires not only detecting the location and the extent of the damage but also identifying the damaged part. To train a…