Related papers: Dataset Enhancement with Instance-Level Augmentati…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Data augmentation is essential to achieve state-of-the-art performance in many deep learning applications. However, the most effective augmentation techniques become computationally prohibitive for even medium-sized datasets. To address…

Source-free domain-adaptive object detection is an interesting but scarcely addressed topic. It aims at adapting a source-pretrained detector to a distinct target domain without resorting to source data during adaptation. So far, there is…

In this paper, we propose a novel data augmentation technique (ANDA) applied to the Salient Object Detection (SOD) context. Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and…

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content…

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, and training directly…

Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often fail by making global changes to the image, inserting objects…

Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and…

For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data. As a widely used data augmentation method, GT-sample effectively improves detection…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

Data augmentation is an effective and universal technique for improving generalization performance of deep neural networks. It could enrich diversity of training samples that is essential in medical image segmentation tasks because 1) the…

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

Open-set face recognition refers to a scenario in which biometric systems have incomplete knowledge of all existing subjects. Therefore, they are expected to prevent face samples of unregistered subjects from being identified as previously…

We propose a novel data augmentation method named 'FenceMask' that exhibits outstanding performance in various computer vision tasks. It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between…

Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefore they require…

Recently, Dynamic Vision Sensors (DVSs) sparked a lot of interest due to their inherent advantages over conventional RGB cameras. These advantages include a low latency, a high dynamic range and a low energy consumption. Nevertheless, the…

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a…

Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge.…