Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation
- URL: http://arxiv.org/abs/2412.06470v1
- Date: Mon, 09 Dec 2024 13:15:52 GMT
- Title: Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation
- Authors: Fei Wu, Pablo Marquez-Neila, Hedyeh Rafi-Tarii, Raphael Sznitman,
- Abstract summary: Multi-class semantic segmentation remains a cornerstone challenge in computer vision.
Active Learning (AL) mitigates this challenge by selecting data points for annotation strategically.
We present OREAL, a novel patch-based AL method designed for multi-class semantic segmentation.
- Score: 11.077512630548153
- License:
- Abstract: Multi-class semantic segmentation remains a cornerstone challenge in computer vision. Yet, dataset creation remains excessively demanding in time and effort, especially for specialized domains. Active Learning (AL) mitigates this challenge by selecting data points for annotation strategically. However, existing patch-based AL methods often overlook boundary pixels critical information, essential for accurate segmentation. We present OREAL, a novel patch-based AL method designed for multi-class semantic segmentation. OREAL enhances boundary detection by employing maximum aggregation of pixel-wise uncertainty scores. Additionally, we introduce one-vs-rest entropy, a novel uncertainty score function that computes class-wise uncertainties while achieving implicit class balancing during dataset creation. Comprehensive experiments across diverse datasets and model architectures validate our hypothesis.
Related papers
- Propensity-driven Uncertainty Learning for Sample Exploration in Source-Free Active Domain Adaptation [19.620523416385346]
Source-free active domain adaptation (SFADA) addresses the challenge of adapting a pre-trained model to new domains without access to source data.
This scenario is particularly relevant in real-world applications where data privacy, storage limitations, or labeling costs are significant concerns.
We propose the Propensity-driven Uncertainty Learning (ProULearn) framework to effectively select more informative samples without frequently requesting human annotations.
arXiv Detail & Related papers (2025-01-23T10:05:25Z) - Annotation-Efficient Polyp Segmentation via Active Learning [45.59503015577479]
We propose a deep active learning framework for annotation-efficient polyp segmentation.
In practice, we measure the uncertainty of each sample by examining the similarity between features masked by the prediction map of the polyp and the background area.
We show that our proposed method achieved state-of-the-art performance compared to other competitors on both a public dataset and a large-scale in-house dataset.
arXiv Detail & Related papers (2024-03-21T12:25:17Z) - Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data.
One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is.
This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
arXiv Detail & Related papers (2024-01-18T08:12:23Z) - MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation [2.0293118701268154]
We propose a novel MultiResolution Feature Perturbation (MRFP) technique to randomize domain-specific fine-grained features and perturb style of coarse features.
MRFP helps state-of-the-art deep neural networks to learn robust domain invariant features for simulation-to-real semantic segmentation.
arXiv Detail & Related papers (2023-11-30T08:02:49Z) - Maturity-Aware Active Learning for Semantic Segmentation with
Hierarchically-Adaptive Sample Assessment [18.65352271757926]
"Maturity-Aware Distribution Breakdown-based Active Learning" (MADBAL) is an AL method that takes into account the different "sample" definitions jointly.
MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly.
It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our experiments.
arXiv Detail & Related papers (2023-08-28T21:13:04Z) - Learning Confident Classifiers in the Presence of Label Noise [5.551384206194696]
This paper proposes a probabilistic model for noisy observations that allows us to build a confident classification and segmentation models.
Our experiments show that our algorithm outperforms state-of-the-art solutions for the considered classification and segmentation problems.
arXiv Detail & Related papers (2023-01-02T04:27:25Z) - Active Pointly-Supervised Instance Segmentation [106.38955769817747]
We present an economic active learning setting, named active pointly-supervised instance segmentation (APIS)
APIS starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object.
The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset.
arXiv Detail & Related papers (2022-07-23T11:25:24Z) - Consistency and Diversity induced Human Motion Segmentation [231.36289425663702]
We propose a novel Consistency and Diversity induced human Motion (CDMS) algorithm.
Our model factorizes the source and target data into distinct multi-layer feature spaces.
A multi-mutual learning strategy is carried out to reduce the domain gap between the source and target data.
arXiv Detail & Related papers (2022-02-10T06:23:56Z) - Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
arXiv Detail & Related papers (2021-12-12T06:11:16Z) - Reliable Shot Identification for Complex Event Detection via
Visual-Semantic Embedding [72.9370352430965]
We propose a visual-semantic guided loss method for event detection in videos.
Motivated by curriculum learning, we introduce a negative elastic regularization term to start training the classifier with instances of high reliability.
An alternative optimization algorithm is developed to solve the proposed challenging non-net regularization problem.
arXiv Detail & Related papers (2021-10-12T11:46:56Z) - Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label.
Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data.
This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
arXiv Detail & Related papers (2020-02-19T08:35:15Z)
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.