Hierarchical Semantic Segmentation using Psychometric Learning
- URL: http://arxiv.org/abs/2107.03212v1
- Date: Wed, 7 Jul 2021 13:38:33 GMT
- Title: Hierarchical Semantic Segmentation using Psychometric Learning
- Authors: Lu Yin, Vlado Menkovski, Shiwei Liu, Mykola Pechenizkiy
- Abstract summary: We develop a novel approach to collect segmentation annotations from experts based on psychometric testing.
Our method consists of the psychometric testing procedure, active query selection, query enhancement, and a deep metric learning model.
We show the merits of our method with evaluation on the synthetically generated image, aerial image and histology image.
- Score: 17.417302703539367
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Assigning meaning to parts of image data is the goal of semantic image
segmentation. Machine learning methods, specifically supervised learning is
commonly used in a variety of tasks formulated as semantic segmentation. One of
the major challenges in the supervised learning approaches is expressing and
collecting the rich knowledge that experts have with respect to the meaning
present in the image data. Towards this, typically a fixed set of labels is
specified and experts are tasked with annotating the pixels, patches or
segments in the images with the given labels. In general, however, the set of
classes does not fully capture the rich semantic information present in the
images. For example, in medical imaging such as histology images, the different
parts of cells could be grouped and sub-grouped based on the expertise of the
pathologist.
To achieve such a precise semantic representation of the concepts in the
image, we need access to the full depth of knowledge of the annotator. In this
work, we develop a novel approach to collect segmentation annotations from
experts based on psychometric testing. Our method consists of the psychometric
testing procedure, active query selection, query enhancement, and a deep metric
learning model to achieve a patch-level image embedding that allows for
semantic segmentation of images. We show the merits of our method with
evaluation on the synthetically generated image, aerial image and histology
image.
Related papers
- Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey [49.47197748663787]
This review aims to provide a first comprehensive and organized overview of the state-of-the-art research results on pseudo-label methods in the field of semi-supervised semantic segmentation.
In addition, we explore the application of pseudo-label technology in medical and remote-sensing image segmentation.
arXiv Detail & Related papers (2024-03-04T10:18:38Z) - Learning Semantic Segmentation with Query Points Supervision on Aerial Images [57.09251327650334]
We present a weakly supervised learning algorithm to train semantic segmentation algorithms.
Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation.
arXiv Detail & Related papers (2023-09-11T14:32:04Z) - HIRL: A General Framework for Hierarchical Image Representation Learning [54.12773508883117]
We propose a general framework for Hierarchical Image Representation Learning (HIRL)
This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained.
Based on a probabilistic factorization, HIRL learns the most fine-grained semantics by an off-the-shelf image SSL approach and learns multiple coarse-grained semantics by a novel semantic path discrimination scheme.
arXiv Detail & Related papers (2022-05-26T05:13:26Z) - Semi-supervised Contrastive Learning for Label-efficient Medical Image
Segmentation [11.935891325600952]
We propose a supervised local contrastive loss that leverages limited pixel-wise annotation to force pixels with the same label to gather around in the embedding space.
With different amounts of labeled data, our methods consistently outperform the state-of-the-art contrast-based methods and other semi-supervised learning techniques.
arXiv Detail & Related papers (2021-09-15T16:23:48Z) - Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image
Segmentation [6.889911520730388]
We aim to boost the performance of semi-supervised learning for medical image segmentation with limited labels.
We learn latent representations directly at feature-level by imposing contrastive loss on unlabeled images.
We conduct experiments on an MRI and a CT segmentation dataset and demonstrate that the proposed method achieves state-of-the-art performance.
arXiv Detail & Related papers (2021-05-27T03:27:58Z) - Semantic Segmentation with Generative Models: Semi-Supervised Learning
and Strong Out-of-Domain Generalization [112.68171734288237]
We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels.
We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images.
We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
arXiv Detail & Related papers (2021-04-12T21:41:25Z) - Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences.
In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference.
Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
arXiv Detail & Related papers (2020-07-03T21:53:46Z) - Learning unbiased zero-shot semantic segmentation networks via
transductive transfer [14.55508599873219]
We propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation.
Our method assumes both the source images with full pixel-level labels and unlabeled target images are available during training.
arXiv Detail & Related papers (2020-07-01T14:25:13Z) - Hierarchical Image Classification using Entailment Cone Embeddings [68.82490011036263]
We first inject label-hierarchy knowledge into an arbitrary CNN-based classifier.
We empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance.
arXiv Detail & Related papers (2020-04-02T10:22:02Z) - Deep Semantic Segmentation of Natural and Medical Images: A Review [17.620924936500725]
The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class.
In the medical image analysis domain, image segmentation can be used for image-guided interventions, radiotherapy, or improved radiological diagnostics.
In this review, we categorize the leading deep learning-based medical and non-medical image segmentation solutions into six main groups of deep architectural, data synthesis-based, loss function-based, sequenced models, weakly supervised, and multi-task methods.
arXiv Detail & Related papers (2019-10-16T06:35:50Z)
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.