RankSEG: A Consistent Ranking-based Framework for Segmentation
- URL: http://arxiv.org/abs/2206.13086v3
- Date: Mon, 13 Nov 2023 06:16:09 GMT
- Title: RankSEG: A Consistent Ranking-based Framework for Segmentation
- Authors: Ben Dai and Chunlin Li
- Abstract summary: We establish a theoretical foundation of segmentation with respect to the Dice/IoU metrics, including the Bayes rule and Dice-/IoU-calibration.
We propose a novel consistent ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of the Bayes segmentation rule.
- Score: 5.166970737490847
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Segmentation has emerged as a fundamental field of computer vision and
natural language processing, which assigns a label to every pixel/feature to
extract regions of interest from an image/text. To evaluate the performance of
segmentation, the Dice and IoU metrics are used to measure the degree of
overlap between the ground truth and the predicted segmentation. In this paper,
we establish a theoretical foundation of segmentation with respect to the
Dice/IoU metrics, including the Bayes rule and Dice-/IoU-calibration, analogous
to classification-calibration or Fisher consistency in classification. We prove
that the existing thresholding-based framework with most operating losses are
not consistent with respect to the Dice/IoU metrics, and thus may lead to a
suboptimal solution. To address this pitfall, we propose a novel consistent
ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of
the Bayes segmentation rule. Three numerical algorithms with GPU parallel
execution are developed to implement the proposed framework in large-scale and
high-dimensional segmentation. We study statistical properties of the proposed
framework. We show it is Dice-/IoU-calibrated, and its excess risk bounds and
the rate of convergence are also provided. The numerical effectiveness of
RankDice/mRankDice is demonstrated in various simulated examples and
Fine-annotated CityScapes, Pascal VOC and Kvasir-SEG datasets with
state-of-the-art deep learning architectures.
Related papers
- Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification [120.37051160567277]
This paper proposes a novel measure named Top-K Pairwise Ranking (TKPR)
A series of analyses show that TKPR is compatible with existing ranking-based measures.
On the other hand, we establish a sharp generalization bound for the proposed framework based on a novel technique named data-dependent contraction.
arXiv Detail & Related papers (2024-07-09T09:36:37Z) - Make it more specific: A novel uncertainty based airway segmentation
application on 3D U-Net and its variants [7.510433578643361]
The most popular algorithms in medical segmentation, 3D U-Net and its variants, can directly implement the task of lung trachea segmentation.
A research gap exists because a great amount of state-of-the-art DL algorithms are vanilla 3D U-Net structures.
We propose two different network structures Branch-Level U-Net (B-UNet) and Branch-Level CE-UNet (B-CE-UNet) which are based on U-Net structure.
arXiv Detail & Related papers (2024-02-12T04:40:19Z) - AttenScribble: Attentive Similarity Learning for Scribble-Supervised
Medical Image Segmentation [5.8447004333496855]
In this paper, we present a straightforward yet effective scribble supervised learning framework.
We create a pluggable spatial self-attention module which could be attached on top of any internal feature layers of arbitrary fully convolutional network (FCN) backbone.
This attentive similarity leads to a novel regularization loss that imposes consistency between segmentation prediction and visual affinity.
arXiv Detail & Related papers (2023-12-11T18:42:18Z) - Revisiting Evaluation Metrics for Semantic Segmentation: Optimization
and Evaluation of Fine-grained Intersection over Union [113.20223082664681]
We propose the use of fine-grained mIoUs along with corresponding worst-case metrics.
These fine-grained metrics offer less bias towards large objects, richer statistical information, and valuable insights into model and dataset auditing.
Our benchmark study highlights the necessity of not basing evaluations on a single metric and confirms that fine-grained mIoUs reduce the bias towards large objects.
arXiv Detail & Related papers (2023-10-30T03:45:15Z) - Panoptic Out-of-Distribution Segmentation [11.388678390784195]
We propose Panoptic Out-of Distribution for joint pixel-level semantic in-distribution and out-of-distribution classification with instance prediction.
We make the dataset, code, and trained models publicly available at http://pods.cs.uni-freiburg.de.
arXiv Detail & Related papers (2023-10-18T08:38:31Z) - FV-UPatches: Enhancing Universality in Finger Vein Recognition [0.6299766708197883]
We propose a universal learning-based framework, which achieves generalization while training with limited data.
The proposed framework shows application potential in other vein-based biometric recognition as well.
arXiv Detail & Related papers (2022-06-02T14:20:22Z) - PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban
Meshes [3.058685580689605]
We introduce a novel deep learning-based framework to interpret 3D urban scenes represented as textured meshes.
Our framework achieves semantic segmentation in two steps: planarity-sensible over-segmentation followed by semantic classification.
Our approach outperforms the state-of-the-art methods in terms of boundary quality and mean IoU (intersection over union)
arXiv Detail & Related papers (2022-02-07T14:16:10Z) - Distribution-aware Margin Calibration for Semantic Segmentation in
Images [78.65312390695038]
Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation.
Direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable.
We propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution.
arXiv Detail & Related papers (2021-12-21T22:38:25Z) - Semantic Distribution-aware Contrastive Adaptation for Semantic
Segmentation [50.621269117524925]
Domain adaptive semantic segmentation refers to making predictions on a certain target domain with only annotations of a specific source domain.
We present a semantic distribution-aware contrastive adaptation algorithm that enables pixel-wise representation alignment.
We evaluate SDCA on multiple benchmarks, achieving considerable improvements over existing algorithms.
arXiv Detail & Related papers (2021-05-11T13:21:25Z) - Adversarial Feature Augmentation and Normalization for Visual
Recognition [109.6834687220478]
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings.
We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
arXiv Detail & Related papers (2021-03-22T20:36:34Z) - Self-Supervised Tuning for Few-Shot Segmentation [82.32143982269892]
Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples.
Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space.
This paper presents an adaptive framework tuning, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme.
arXiv Detail & Related papers (2020-04-12T03:53:53Z)
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.