Related papers: MURAUER: Mapping Unlabeled Real Data for Label AUs…

We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…

Object pose estimation is a necessary prerequisite for autonomous robotic manipulation, but the presence of symmetry increases the complexity of the pose estimation task. Existing methods for object pose estimation output a single 6D pose.…

Supervised machine learning assumes that labeled data provide accurate measurements of the concepts models are meant to learn. Yet in practice, human labeling introduces systematic variation arising from ambiguous items, divergent…

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the…

Nowadays, the need for large amounts of carefully and complexly annotated data for the training of computer vision modules continues to grow. Furthermore, although the research community presents state of the art solutions to many problems,…

Data augmentation is rapidly gaining attention in machine learning. Synthetic data can be generated by simple transformations or through the data distribution. In the latter case, the main challenge is to estimate the label associated to…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence…

In the industrial domain, the pose estimation of multiple texture-less shiny parts is a valuable but challenging task. In this particular scenario, it is impractical to utilize keypoints or other texture information because most of them are…

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…

We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality…

In the medical domain, the lack of large training data sets and benchmarks is often a limiting factor for training deep neural networks. In contrast to expensive manual labeling, computer simulations can generate large and fully labeled…

Training a semantic segmentation model requires a large amount of pixel-level annotation, hampering its application at scale. With computer graphics, we can generate almost unlimited training data with precise annotation. However,a deep…

Metric learning is an important problem in machine learning. It aims to group similar examples together. Existing state-of-the-art metric learning approaches require class labels to learn a metric. As obtaining class labels in all…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training…

Data collection from manual labeling provides domain-specific and task-aligned supervision for data-driven approaches, and a critical mass of well-annotated resources is required to achieve reasonable performance in natural language…

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…