Task-Aware Variational Adversarial Active Learning
- URL: http://arxiv.org/abs/2002.04709v2
- Date: Tue, 8 Dec 2020 05:36:08 GMT
- Title: Task-Aware Variational Adversarial Active Learning
- Authors: Kwanyoung Kim, Dongwon Park, Kwang In Kim, Se Young Chun
- Abstract summary: We propose task-aware variational adversarial AL (TA-VAAL) that modifies task-agnostic VAAL.
Our proposed TA-VAAL outperforms state-of-the-arts on various benchmark datasets for classifications with balanced / imbalanced labels.
- Score: 42.334671410592065
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Often, labeling large amount of data is challenging due to high labeling cost
limiting the application domain of deep learning techniques. Active learning
(AL) tackles this by querying the most informative samples to be annotated
among unlabeled pool. Two promising directions for AL that have been recently
explored are task-agnostic approach to select data points that are far from the
current labeled pool and task-aware approach that relies on the perspective of
task model. Unfortunately, the former does not exploit structures from tasks
and the latter does not seem to well-utilize overall data distribution. Here,
we propose task-aware variational adversarial AL (TA-VAAL) that modifies
task-agnostic VAAL, that considered data distribution of both label and
unlabeled pools, by relaxing task learning loss prediction to ranking loss
prediction and by using ranking conditional generative adversarial network to
embed normalized ranking loss information on VAAL. Our proposed TA-VAAL
outperforms state-of-the-arts on various benchmark datasets for classifications
with balanced / imbalanced labels as well as semantic segmentation and its
task-aware and task-agnostic AL properties were confirmed with our in-depth
analyses.
Related papers
- Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling [6.771578432805963]
Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples.
We introduce novel techniques that significantly improve the use of abundant unlabeled data during training.
We demonstrate the superior performance of our approach over the state of the art on various image classification and segmentation benchmark datasets.
arXiv Detail & Related papers (2024-08-23T00:35:07Z) - MyriadAL: Active Few Shot Learning for Histopathology [10.652626309100889]
We introduce an active few shot learning framework, Myriad Active Learning (MAL)
MAL includes a contrastive-learning encoder, pseudo-label generation, and novel query sample selection in the loop.
Experiments on two public histopathology datasets show that MAL has superior test accuracy, macro F1-score, and label efficiency compared to prior works.
arXiv Detail & Related papers (2023-10-24T20:08:15Z) - XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification.
XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations.
Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
arXiv Detail & Related papers (2023-10-09T08:07:04Z) - Identify ambiguous tasks combining crowdsourced labels by weighting
Areas Under the Margin [13.437403258942716]
Ambiguous tasks might fool expert workers, which is often harmful for the learning step.
We adapt the Area Under the Margin (AUM) to identify mislabeled data in crowdsourced learning scenarios.
We show that the WAUM can help discarding ambiguous tasks from the training set, leading to better generalization performance.
arXiv Detail & Related papers (2022-09-30T11:16:20Z) - Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task
Distributions [8.88133567816717]
We name this problem as Semi-supervised meta-learning with Evolving Task diStributions, abbreviated as SETS.
We propose an OOD Robust and knowleDge presErved semi-supeRvised meta-learning approach (ORDER) to tackle these two major challenges.
Specifically, our ORDER introduces a novel mutual information regularization to robustify the model with unlabeled OOD data and adopts an optimal transport regularization to remember previously learned knowledge in feature space.
arXiv Detail & Related papers (2022-09-03T21:22:14Z) - Pareto Optimization for Active Learning under Out-of-Distribution Data
Scenarios [79.02009938011447]
We propose a sampling scheme, which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
Experimental results show its effectiveness on both classical Machine Learning (ML) and Deep Learning (DL) tasks.
arXiv Detail & Related papers (2022-07-04T04:11:44Z) - Active Learning by Feature Mixing [52.16150629234465]
We propose a novel method for batch active learning called ALFA-Mix.
We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions.
We show that inconsistencies in these predictions help discovering features that the model is unable to recognise in the unlabelled instances.
arXiv Detail & Related papers (2022-03-14T12:20:54Z) - Using Self-Supervised Pretext Tasks for Active Learning [7.214674613451605]
We propose a novel active learning approach that utilizes self-supervised pretext tasks and a unique data sampler to select data that are both difficult and representative.
The pretext task learner is trained on the unlabeled set, and the unlabeled data are sorted and grouped into batches by their pretext task losses.
In each iteration, the main task model is used to sample the most uncertain data in a batch to be annotated.
arXiv Detail & Related papers (2022-01-19T07:58:06Z) - CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and
Segmentation [60.28924281991539]
We propose a novel Class-agnostic Semi-supervised Pretraining (CaSP) framework to achieve a more favorable task-specificity balance.
Using 3.6M unlabeled data, we achieve a remarkable performance gain of 4.7% over ImageNet-pretrained baseline on object detection.
arXiv Detail & Related papers (2021-12-09T14:54:59Z) - Out-distribution aware Self-training in an Open World Setting [62.19882458285749]
We leverage unlabeled data in an open world setting to further improve prediction performance.
We introduce out-distribution aware self-training, which includes a careful sample selection strategy.
Our classifiers are by design out-distribution aware and can thus distinguish task-related inputs from unrelated ones.
arXiv Detail & Related papers (2020-12-21T12:25:04Z)
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.