The Weakly-Labeled Rand Index
- URL: http://arxiv.org/abs/2103.04872v2
- Date: Tue, 9 Mar 2021 02:58:37 GMT
- Title: The Weakly-Labeled Rand Index
- Authors: Dylan Stewart, Anna Hampton, Alina Zare, Jeff Dale, James Keller
- Abstract summary: SAS surveys produce imagery with large regions of transition between seabed types.
It is difficult to label and segment the imagery and, furthermore, challenging to score the image segmentations appropriately.
- Score: 2.989889278970106
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Synthetic Aperture Sonar (SAS) surveys produce imagery with large regions of
transition between seabed types. Due to these regions, it is difficult to label
and segment the imagery and, furthermore, challenging to score the image
segmentations appropriately. While there are many approaches to quantify
performance in standard crisp segmentation schemes, drawing hard boundaries in
remote sensing imagery where gradients and regions of uncertainty exist is
inappropriate. These cases warrant weak labels and an associated appropriate
scoring approach. In this paper, a labeling approach and associated modified
version of the Rand index for weakly-labeled data is introduced to address
these issues. Results are evaluated with the new index and compared to
traditional segmentation evaluation methods. Experimental results on a SAS data
set containing must-link and cannot-link labels show that our Weakly-Labeled
Rand index scores segmentations appropriately in reference to qualitative
performance and is more suitable than traditional quantitative metrics for
scoring weakly-labeled data.
Related papers
- Progressive Feature Self-reinforcement for Weakly Supervised Semantic
Segmentation [55.69128107473125]
We propose a single-stage approach for Weakly Supervised Semantic (WSSS) with image-level labels.
We adaptively partition the image content into deterministic regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing.
Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels.
arXiv Detail & Related papers (2023-12-14T13:21:52Z) - Semi-Supervised Semantic Segmentation With Region Relevance [28.92449538610617]
Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones.
The most common approach is to generate pseudo-labels for unlabeled images to augment the training data.
This paper proposes a Region Relevance Network (RRN) to alleviate the problem mentioned above.
arXiv Detail & Related papers (2023-04-23T04:51:27Z) - Long-tailed Extreme Multi-label Text Classification with Generated
Pseudo Label Descriptions [28.416742933744942]
This paper addresses the challenge of tail label prediction by proposing a novel approach.
It combines the effectiveness of a trained bag-of-words (BoW) classifier in generating informative label descriptions under severe data scarce conditions.
The proposed approach achieves state-of-the-art performance on XMTC benchmark datasets and significantly outperforms the best methods so far in the tail label prediction.
arXiv Detail & Related papers (2022-04-02T23:42:32Z) - PointMatch: A Consistency Training Framework for Weakly Supervised
Semantic Segmentation of 3D Point Clouds [117.77841399002666]
We propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself.
The proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets.
arXiv Detail & Related papers (2022-02-22T07:26:31Z) - POPCORN: Progressive Pseudo-labeling with Consistency Regularization and
Neighboring [3.4253416336476246]
Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of images and the lack of method generalization to unseen domains.
We propose POPCORN, a novel method combining consistency regularization and pseudo-labeling designed for image segmentation.
arXiv Detail & Related papers (2021-09-13T23:36:36Z) - Addressing Annotation Imprecision for Tree Crown Delineation Using the
RandCrowns Index [2.6144305160661228]
Tree crown delineation provides key information from remote sensing images for forestry, ecology, and management.
Current evaluation methods do not account for uncertainty in annotations.
We address these limitations using an adaptation of the Rand index for weakly-labeled crown delineation that we call RandCrowns.
arXiv Detail & Related papers (2021-05-05T16:57:23Z) - Delving Deep into Label Smoothing [112.24527926373084]
Label smoothing is an effective regularization tool for deep neural networks (DNNs)
We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category.
arXiv Detail & Related papers (2020-11-25T08:03:11Z) - PseudoSeg: Designing Pseudo Labels for Semantic Segmentation [78.35515004654553]
We present a re-design of pseudo-labeling to generate structured pseudo labels for training with unlabeled or weakly-labeled data.
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
arXiv Detail & Related papers (2020-10-19T17:59:30Z) - Superpixel-Guided Label Softening for Medical Image Segmentation [31.989873877526424]
We propose superpixel-based label softening for medical image segmentation.
We show that this method achieves overall superior segmentation performances to baseline and comparison methods for both 3D and 2D medical images.
arXiv Detail & Related papers (2020-07-17T10:55:59Z) - MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative
Adversarial Network [51.84251358009803]
We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting.
We perform augmentation by randomly sampling sensible labels from the label space of the few labelled examples available.
Our method surpasses the baseline with only 20% of the labelled examples used to train the baseline.
arXiv Detail & Related papers (2020-06-11T17:14:55Z) - Few-shot Slot Tagging with Collapsed Dependency Transfer and
Label-enhanced Task-adaptive Projection Network [61.94394163309688]
We propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model -- TapNet.
Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
arXiv Detail & Related papers (2020-06-10T07:50:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.