Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Hwang, Sehyun"'
This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box annotation pro
Externí odkaz:
http://arxiv.org/abs/2405.20729
Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are error-pron
Externí odkaz:
http://arxiv.org/abs/2403.10820
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an oracle for
Externí odkaz:
http://arxiv.org/abs/2309.09319
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per superpixel ins
Externí odkaz:
http://arxiv.org/abs/2303.16817
This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object classes through attentions drawn by an image classification network. Sinc
Externí odkaz:
http://arxiv.org/abs/2212.07579
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch between s
Externí odkaz:
http://arxiv.org/abs/2208.06604
Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training debiased class
Externí odkaz:
http://arxiv.org/abs/2206.10843
Autor:
Karthikeyan, Sreejith, Hwang, Sehyun, Sibakoti, Mandip, Bontrager, Timothy, Liptak, Richard W., Campbell, Stephen A.
Publikováno v:
In Applied Surface Science 1 November 2019 493:105-111
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.