Related papers: SUPClust: Active Learning at the Boundaries

SUPClust: Active Learning at the Boundaries

URL: http://arxiv.org/abs/2403.03741v1
Date: Wed, 6 Mar 2024 14:30:09 GMT
Title: SUPClust: Active Learning at the Boundaries
Authors: Yuta Ono, Till Aczel, Benjamin Estermann, Roger Wattenhofer
Abstract summary: We propose a novel active learning method called SUPClust that seeks to identify points at the decision boundary between classes. We demonstrate experimentally that labeling these points leads to strong model performance.
Score: 23.573986817769025
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Active learning is a machine learning paradigm designed to optimize model performance in a setting where labeled data is expensive to acquire. In this work, we propose a novel active learning method called SUPClust that seeks to identify points at the decision boundary between classes. By targeting these points, SUPClust aims to gather information that is most informative for refining the model's prediction of complex decision regions. We demonstrate experimentally that labeling these points leads to strong model performance. This improvement is observed even in scenarios characterized by strong class imbalance.

Related papers

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence [60.37934652213881]
Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation. We present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead.
arXiv Detail & Related papers (2024-07-26T17:51:58Z)
Mean-AP Guided Reinforced Active Learning for Object Detection [31.304039641225504]
This paper introduces Mean-AP Guided Reinforced Active Learning for Object Detection (MGRAL) MGRAL is a novel approach that leverages the concept of expected model output changes as informativeness for deep detection networks. Our approach demonstrates strong performance, establishing a new paradigm in reinforcement learning-based active learning for object detection.
arXiv Detail & Related papers (2023-10-12T14:59:22Z)
Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z)
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)
MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
arXiv Detail & Related papers (2021-07-23T06:57:08Z)
Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes [78.23907801786827]
We introduce generalizations that ensure that our approach is both cost-aware and allows for fine-grained selection of examples through partially labeled scenes. Our experiments on a real-world, large-scale self-driving dataset suggest that fine-grained selection can improve the performance across perception, prediction, and downstream planning tasks.
arXiv Detail & Related papers (2021-04-08T17:57:41Z)
Toward Optimal Probabilistic Active Learning Using a Bayesian Approach [4.380488084997317]
Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art.
arXiv Detail & Related papers (2020-06-02T15:59:42Z)
Incremental Object Detection via Meta-Learning [77.55310507917012]
We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
arXiv Detail & Related papers (2020-03-17T13:40:00Z)
Information Condensing Active Learning [4.769747792846005]
We introduce Information Condensing Active Learning (ICAL), a batch mode model Active Learning (AL) method targeted at Deep Bayesian Active Learning. ICAL uses the Hilbert Schmidt Independence Criterion (HSIC) to measure the strength of the dependency between a candidate batch of points and the unlabeled set. We show significant improvements in terms of model accuracy and negative log likelihood (NLL) on several image datasets compared to state of the art batch mode AL methods for deep learning.
arXiv Detail & Related papers (2020-02-18T22:55:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.