mlsanityData to 7 Oct 2026

PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings

arXiv 2211.11546 ↗First posted 21 Nov 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning (AL) can be used to reduce this burden. Existing techniques typically involve picking images to be annotated and providing annotations for all tasks. In this paper, we show that it is more effective to select not only the images to be annotated but also a subset of tasks for which to provide annotations at each AL iteration. Furthermore, the annotations that are provided can be used to guess pseudo-labels for the tasks that remain unannotated. We demonstrate the effectiveness of our approach on several popular multi-task datasets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 21 Nov 2022.

Builds on

23 of 48 references.

References · 23

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  5. 2017Deep Bayesian Active Learning with Image Datacited by 812
  6. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  7. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  8. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  9. 2019Learning Loss for Active Learningcited by 335
  10. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  11. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  12. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
11 more
  1. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  2. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  3. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  4. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  5. 2020Masksembles for Uncertainty Estimationcited by 88
  6. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  7. 2019Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Visioncited by 64
  8. 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
  9. 2016Trace Norm Regularised Deep Multi-Task Learningcited by 50
  10. 2021DEBOSH: Deep Bayesian Shape Optimizationcited by 14
  11. 2013Approximating the Bethe partition functioncited by 3

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Enabling Uncertainty Estimation in Iterative Neural Networkscited by 11
  2. 2024IT3: Idempotent Test-Time Trainingcited by 6
  3. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5