Related papers: Transferability of labels between multilens camera…

A popular series of style transfer methods apply a style to a content image by controlling mean and covariance of values in early layers of a feature stack. This is insufficient for transferring styles that have strong structure across…

Collecting pixel-level labels for medical datasets can be a laborious and expensive process, and enhancing segmentation performance with a scarcity of labeled data is a crucial challenge. This work introduces AugPaint, a data augmentation…

Many interactive image segmentation techniques are based on semi-supervised learning. The user may label some pixels from each object and the SSL algorithm will propagate the labels from the labeled to the unlabeled pixels, finding object…

Based on transformation optics, a strategy is proposed to expose the inner one-dimensional space of a wave field inside a beam volume to the surface of the propagation medium and extend the space from one-dimensional to two-dimensional,…

In this paper we propose a method for transfer learning of endoscopic images. For transferring between features obtained from images taken by different (old and new) endoscopes, we extend the Max-Margin Domain Transfer (MMDT) proposed by…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

Real-world recognition system often encounters the challenge of unseen labels. To identify such unseen labels, multi-label zero-shot learning (ML-ZSL) focuses on transferring knowledge by a pre-trained textual label embedding (e.g., GloVe).…

Detecting object-level changes between two images across possibly different views is a core task in many applications that involve visual inspection or camera surveillance. Existing change-detection approaches suffer from three major…

Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-supervised learning methods consists in the effective use of…

The mutual incompatibility of distinct spectroscopic systems is among the most limiting factors in Laser-Induced Breakdown Spectroscopy (LIBS). The cost related to setting up a new LIBS system is increased, as its extensive calibration is…

Image segmentation is an important task in many medical applications. Methods based on convolutional neural networks attain state-of-the-art accuracy; however, they typically rely on supervised training with large labeled datasets. Labeling…

The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated. Lack of time…

This paper proposes an approach for rapid bounding box annotation for object detection datasets. The procedure consists of two stages: The first step is to annotate a part of the dataset manually, and the second step proposes annotations…

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to…

Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports…

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Reliable road segmentation in all weather conditions is critical for intelligent transportation applications, autonomous vehicles and advanced driver's assistance systems. For robust performance, all weather conditions should be included in…

Multi-target state estimation refers to estimating the number of targets and their trajectories in a surveillance area using measurements contaminated with noise and clutter. In the Bayesian paradigm, the most common approach to…

The vast amount of unlabeled multi-temporal and multi-sensor remote sensing data acquired by the many Earth Observation satellites present a challenge for change detection. Recently, many generative model-based methods have been proposed…

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target image; and the transformed atlas labels…