Semantic Segmentation with Labeling Uncertainty and Class Imbalance
- URL: http://arxiv.org/abs/2102.04566v1
- Date: Mon, 8 Feb 2021 22:53:33 GMT
- Title: Semantic Segmentation with Labeling Uncertainty and Class Imbalance
- Authors: Patrik Ol\~a Bressan, Jos\'e Marcato Junior, Jos\'e Augusto Correa
Martins, Diogo Nunes Gon\c{c}alves, Daniel Matte Freitas, Lucas Prado Osco,
Jonathan de Andrade Silva, Zhipeng Luo, Jonathan Li, Raymundo Cordero Garcia,
Wesley Nunes Gon\c{c}alves
- Abstract summary: We present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process.
The pixel-wise weights are used during training to increase or decrease the importance of the pixels.
- Score: 19.512800180525087
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Recently, methods based on Convolutional Neural Networks (CNN) achieved
impressive success in semantic segmentation tasks. However, challenges such as
the class imbalance and the uncertainty in the pixel-labeling process are not
completely addressed. As such, we present a new approach that calculates a
weight for each pixel considering its class and uncertainty during the labeling
process. The pixel-wise weights are used during training to increase or
decrease the importance of the pixels. Experimental results show that the
proposed approach leads to significant improvements in three challenging
segmentation tasks in comparison to baseline methods. It was also proved to be
more invariant to noise. The approach presented here may be used within a wide
range of semantic segmentation methods to improve their robustness.
Related papers
- Instance-wise Uncertainty for Class Imbalance in Semantic Segmentation [4.147659576493158]
State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and be overconfident in predictions.
This is particularly problematic in semantic segmentation due to inherent class imbalance.
A novel training methodology specifically designed for semantic segmentation is presented.
arXiv Detail & Related papers (2024-07-17T14:38:32Z) - Breaking the Barrier: Selective Uncertainty-based Active Learning for
Medical Image Segmentation [5.5575224613422725]
Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance.
We introduce a novel approach called the Selective Uncertainty-based AL, avoiding the conventional practice of summing up the metrics of all pixels.
Our method showed substantial improvements across five different uncertainty-based methods and two distinct datasets.
arXiv Detail & Related papers (2024-01-29T16:59:39Z) - 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) - NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic
Segmentation [87.50830107535533]
Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time.
Current approaches to semi-supervised semantic segmentation work by predicting pseudo-labels for each pixel from a class-wise probability distribution output by a model.
In this work, we move one step forward by adapting NPs to semi-supervised semantic segmentation, resulting in a new model called NP-SemiSeg.
arXiv Detail & Related papers (2023-08-05T12:42:15Z) - Incremental Learning in Semantic Segmentation from Image Labels [18.404068463921426]
Existing semantic segmentation approaches achieve impressive results, but struggle to update their models incrementally as new categories are uncovered.
This paper proposes a novel framework for Weakly Incremental Learning for Semantics, that aims at learning to segment new classes from cheap and largely available image-level labels.
As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.
arXiv Detail & Related papers (2021-12-03T12:47:12Z) - Superpixel-guided Iterative Learning from Noisy Labels for Medical Image
Segmentation [24.557755528031453]
We develop a robust iterative learning strategy that combines noise-aware training of segmentation network and noisy label refinement.
Experiments on two benchmarks show that our method outperforms recent state-of-the-art approaches.
arXiv Detail & Related papers (2021-07-21T14:27:36Z) - Mixed Supervision Learning for Whole Slide Image Classification [88.31842052998319]
We propose a mixed supervision learning framework for super high-resolution images.
During the patch training stage, this framework can make use of coarse image-level labels to refine self-supervised learning.
A comprehensive strategy is proposed to suppress pixel-level false positives and false negatives.
arXiv Detail & Related papers (2021-07-02T09:46:06Z) - Semi-supervised Semantic Segmentation with Directional Context-aware
Consistency [66.49995436833667]
We focus on the semi-supervised segmentation problem where only a small set of labeled data is provided with a much larger collection of totally unlabeled images.
A preferred high-level representation should capture the contextual information while not losing self-awareness.
We present the Directional Contrastive Loss (DC Loss) to accomplish the consistency in a pixel-to-pixel manner.
arXiv Detail & Related papers (2021-06-27T03:42:40Z) - A Closer Look at Self-training for Zero-Label Semantic Segmentation [53.4488444382874]
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning.
Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models.
We propose a consistency regularizer to filter out noisy pseudo-labels by taking the intersections of the pseudo-labels generated from different augmentations of the same image.
arXiv Detail & Related papers (2021-04-21T14:34:33Z) - Contrastive Rendering for Ultrasound Image Segmentation [59.23915581079123]
The lack of sharp boundaries in US images remains an inherent challenge for segmentation.
We propose a novel and effective framework to improve boundary estimation in US images.
Our proposed method outperforms state-of-the-art methods and has the potential to be used in clinical practice.
arXiv Detail & Related papers (2020-10-10T07:14:03Z)
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.