Related papers: A unified framework for manifold landmarking

We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background-foreground and multi-class segmentation tasks in 2D images…

Recent advances in semi-supervised learning methods rely on estimating the categories of unlabeled data using a model trained on the labeled data (pseudo-labeling) and using the unlabeled data for various consistency-based regularization.…

We consider the problem of classification using similarity/distance functions over data. Specifically, we propose a framework for defining the goodness of a (dis)similarity function with respect to a given learning task and propose…

As datasets used in scientific applications become more complex, studying the geometry and topology of data has become an increasingly prevalent part of the data analysis process. This can be seen for example with the growing interest in…

Representation learning is typically applied to only one mode of a data matrix, either its rows or columns. Yet in many applications, there is an underlying geometry to both the rows and the columns. We propose utilizing this coupled…

Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results across a variety of domains. However, the high-level…

Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially labeled facial images. A typical approach is to (1) train a detector on the labeled…

Active learning is a machine learning paradigm designed to optimize model performance in a setting where labeled data is expensive to acquire. In this work, we propose a novel active learning method called SUPClust that seeks to identify…

The training of Generative Adversarial Networks (GANs) requires a large amount of data, stimulating the development of new augmentation methods to alleviate the challenge. Oftentimes, these methods either fail to produce enough new data or…

The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the…

We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistency in annotations…

We propose a new active learning approach for efficiently estimating the geographic range of a species from a limited number of on the ground observations. We model the range of an unmapped species of interest as the weighted combination of…

Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while…

Label noise in training data can significantly degrade a model's generalization performance for supervised learning tasks. Here we focus on the problem that noisy labels are primarily mislabeled samples, which tend to be concentrated near…

Automatic and accurate detection of anatomical landmarks is an essential operation in medical image analysis with a multitude of applications. Recent deep learning methods have improved results by directly encoding the appearance of the…

Active Learning (AL) aims to reduce the labeling burden by interactively selecting the most informative samples from a pool of unlabeled data. While there has been extensive research on improving AL query methods in recent years, some…

We present a general framework of semi-supervised dimensionality reduction for manifold learning which naturally generalizes existing supervised and unsupervised learning frameworks which apply the spectral decomposition. Algorithms derived…

The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of…

Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring…

Active Shape Models (ASM) are an iterative segmentation technique to find a landmark-based contour of an object. In each iteration, a least-squares fit of a plausible shape to some detected target landmarks is determined. Finding these…