Related papers: Reducing the Amount of Real World Data for Object …

Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the available image dataset is insufficiently populated. Synthetic…

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Personalized computed tomography (CT) dosimetry has great potential in assessing patient-specific radiation exposure, supporting risk assessment, and optimizing clinical protocols. The aim of this study is to evaluate the potential of…

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…

Training of a Machine Learning model requires sufficient data. The sufficiency of the data is not always about the quantity, but about the relevancy and reduced redundancy. Data-generating processes create massive amounts of data. When used…

Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that have never been seen during training. This renders our…

Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Infrared (IR) images are essential to improve the visibility of dark or camouflaged objects. Object recognition and segmentation based on a neural network using IR images provide more accuracy and insight than color visible images. But the…

Synthetic data has been a critical tool for training scene text detection and recognition models. On the one hand, synthetic word images have proven to be a successful substitute for real images in training scene text recognizers. On the…

Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. Given the CL training data, generative models can be trained to generate synthetic data to supplement the real…

Deep learning has been successfully applied to several problems related to autonomous driving, often relying on large databases of real target-domain images for proper training. The acquisition of such real-world data is not always possible…

The goal of minimizing misclassification error on a training set is often just one of several real-world goals that might be defined on different datasets. For example, one may require a classifier to also make positive predictions at some…

In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in…

Precise semantic segmentation of crops and weeds is necessary for agricultural weeding robots. However, training deep learning models requires large annotated datasets, which are costly to obtain in real fields. Synthetic data can reduce…

Deep learning approaches are increasingly used to tackle forecasting tasks involving datasets with multiple univariate time series. A key factor in the successful application of these methods is a large enough training sample size, which is…

Visual recognition of materials and their states is essential for understanding the physical world, from identifying wet regions on surfaces or stains on fabrics to detecting infected areas on plants or minerals in rocks. Collecting data…

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional…

Recent advances in deep learning methods have increased the performance of face detection and recognition systems. The accuracy of these models relies on the range of variation provided in the training data. Creating a dataset that…