Related papers: SynCDR : Training Cross Domain Retrieval Models wi…

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…

Deep image translation methods have recently shown excellent results, outputting high-quality images covering multiple modes of the data distribution. There has also been increased interest in disentangling the internal representations…

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of…

Due to the difficulty in collecting large-scale and perfectly aligned paired training data for Under-Display Camera (UDC) image restoration, previous methods resort to monitor-based image systems or simulation-based methods, sacrificing the…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard…

Synthetic medical image generation has evolved as a key technique for neural network training and validation. A core challenge, however, remains in the domain gap between simulations and real data. While deep learning-based domain transfer…

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem…

Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this…

Images of spacecraft photographed from other spacecraft operating in outer space are difficult to come by, especially at a scale typically required for deep learning tasks. Semantic image segmentation, object detection and localization, and…

Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time-consuming to annotate images with semantic labels per…

Recently deep learning - namely convolutional neural networks (CNNs) - have yielded impressive performance for the task of building segmentation on large overhead (e.g., satellite) imagery benchmarks. However, these benchmark datasets only…

With the rapid advancement of image generation techniques, robust forgery detection has become increasingly imperative to ensure the trustworthiness of digital media. Recent research indicates that the learned semantic concepts of…

A long-standing challenge in developing machine learning approaches has been the lack of high-quality labeled data. Recently, models trained with purely synthetic data, here termed synthetic clones, generated using large-scale pre-trained…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical methodologies to transfer learned concepts across different…

Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels…

Unstructured urban environments present unique challenges for scene understanding and generalization due to their complex and diverse layouts. We introduce SynthGenNet, a self-supervised student-teacher architecture designed to enable…