Deep Active Learning in the Presence of Label Noise: A Survey
- URL: http://arxiv.org/abs/2302.11075v2
- Date: Tue, 19 Sep 2023 19:13:07 GMT
- Title: Deep Active Learning in the Presence of Label Noise: A Survey
- Authors: Moseli Mots'oehli, Kyungim Baek
- Abstract summary: Deep active learning has emerged as a powerful tool for training deep learning models within a predefined labeling budget.
We discuss the current state of deep active learning in the presence of label noise, highlighting unique approaches, their strengths, and weaknesses.
We propose exploring contrastive learning methods to derive good image representations that can aid in selecting high-value samples for labeling.
- Score: 1.8945921149936182
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep active learning has emerged as a powerful tool for training deep
learning models within a predefined labeling budget. These models have achieved
performances comparable to those trained in an offline setting. However, deep
active learning faces substantial issues when dealing with classification
datasets containing noisy labels. In this literature review, we discuss the
current state of deep active learning in the presence of label noise,
highlighting unique approaches, their strengths, and weaknesses. With the
recent success of vision transformers in image classification tasks, we provide
a brief overview and consider how the transformer layers and attention
mechanisms can be used to enhance diversity, importance, and uncertainty-based
selection in queries sent to an oracle for labeling. We further propose
exploring contrastive learning methods to derive good image representations
that can aid in selecting high-value samples for labeling in an active learning
setting. We also highlight the need for creating unified benchmarks and
standardized datasets for deep active learning in the presence of label noise
for image classification to promote the reproducibility of research. The review
concludes by suggesting avenues for future research in this area.
Related papers
- Vision-Language Models are Strong Noisy Label Detectors [76.07846780815794]
This paper presents a Denoising Fine-Tuning framework, called DeFT, for adapting vision-language models.
DeFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels.
Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DeFT in both noisy label detection and image classification.
arXiv Detail & Related papers (2024-09-29T12:55:17Z) - Vision-language Assisted Attribute Learning [53.60196963381315]
Attribute labeling at large scale is typically incomplete and partial.
Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during training.
We leverage the available vision-language knowledge to explicitly disclose the missing labels for enhancing model learning.
arXiv Detail & Related papers (2023-12-12T06:45:19Z) - Two-Step Active Learning for Instance Segmentation with Uncertainty and
Diversity Sampling [20.982992381790034]
We propose a post-hoc active learning algorithm that integrates uncertainty-based sampling with diversity-based sampling.
Our proposed algorithm is not only simple and easy to implement, but it also delivers superior performance on various datasets.
arXiv Detail & Related papers (2023-09-28T03:40:30Z) - 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) - Learning to Detect Instance-level Salient Objects Using Complementary
Image Labels [55.049347205603304]
We present the first weakly-supervised approach to the salient instance detection problem.
We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
arXiv Detail & Related papers (2021-11-19T10:15:22Z) - Region-level Active Learning for Cluttered Scenes [60.93811392293329]
We introduce a new strategy that subsumes previous Image-level and Object-level approaches into a generalized, Region-level approach.
We show that this approach significantly decreases labeling effort and improves rare object search on realistic data with inherent class-imbalance and cluttered scenes.
arXiv Detail & Related papers (2021-08-20T14:02:38Z) - Multi-Label Image Classification with Contrastive Learning [57.47567461616912]
We show that a direct application of contrastive learning can hardly improve in multi-label cases.
We propose a novel framework for multi-label classification with contrastive learning in a fully supervised setting.
arXiv Detail & Related papers (2021-07-24T15:00:47Z) - A Survey on Deep Learning with Noisy Labels: How to train your model
when you cannot trust on the annotations? [21.562089974755125]
Several approaches have been proposed to improve the training of deep learning models in the presence of noisy labels.
This paper presents a survey on the main techniques in literature, in which we classify the algorithm in the following groups: robust losses, sample weighting, sample selection, meta-learning, and combined approaches.
arXiv Detail & Related papers (2020-12-05T15:45:20Z) - Attention-Aware Noisy Label Learning for Image Classification [97.26664962498887]
Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision.
The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr.
This paper proposes the attention-aware noisy label learning approach to improve the discriminative capability of the network trained on datasets with potential label noise.
arXiv Detail & Related papers (2020-09-30T15:45:36Z) - Active and Incremental Learning with Weak Supervision [7.2288756536476635]
In this work, we describe combinations of an incremental learning scheme and methods of active learning.
An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset.
We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application.
arXiv Detail & Related papers (2020-01-20T13:21:14Z)
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.