mlsanityData to 7 Oct 2026

Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs

arXiv 2101.12431 ↗First posted 29 Jan 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Heterogeneous multi-task learning (HMTL) is an important topic in multi-task learning (MTL). Most existing HMTL methods usually solve either scenario where all tasks reside in the same input (feature) space yet unnecessarily the consistent output (label) space or scenario where their input (feature) spaces are heterogeneous while the output (label) space is consistent. However, to the best of our knowledge, there is limited study on twofold heterogeneous MTL (THMTL) scenario where the input and the output spaces are both inconsistent or heterogeneous. In order to handle this complicated scenario, in this paper, we design a simple and effective multi-task adaptive learning (MTAL) network to learn multiple tasks in such THMTL setting. Specifically, we explore and utilize the inherent relationship between tasks for knowledge sharing from similar convolution kernels in individual layers of the MTAL network. Then in order to realize the sharing, we weightedly aggregate any pair of convolutional kernels with their similarity greater than some threshold ρ, consequently, our model effectively performs cross-task learning while suppresses the intra-redundancy of the entire network. Finally, we conduct end-to-end training. Our experimental results demonstrate the effectiveness of our method in comparison with the state-of-the-art counterparts.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 29 Jan 2021.

Builds on

34 of 68 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  4. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  6. 2017A Survey on Multi-Task Learningcited by 838
  7. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  8. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  9. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  10. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  11. 2013Predicting Parameters in Deep Learningcited by 223
  12. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
22 more
  1. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  2. 2020Understanding and Improving Information Transfer in Multi-Task Learningcited by 113
  3. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  4. 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
  5. 2015Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Networkcited by 53
  6. 2016Trace Norm Regularised Deep Multi-Task Learningcited by 50
  7. 2017Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approachcited by 43
  8. 2019Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognitioncited by 35
  9. 2019Learning Sparse Sharing Architectures for Multiple Taskscited by 31
  10. 2017BlitzNet: A Real-Time Deep Network for Scene Understandingcited by 29
  11. 2015Embedding Label Structures for Fine-Grained Feature Representationcited by 17
  12. 2019Filter Pruning by Switching to Neighboring CNNs with Good Attributescited by 15
  13. 2014Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Networkcited by 11
  14. 2019Multi-Task Driven Feature Models for Thermal Infrared Trackingcited by 10
  15. 2020Multitask Learning with Single Gradient Step Update for Task Balancingcited by 9
  16. 2020Emerging Relation Network and Task Embedding for Multi-Task Regression Problemscited by 8
  17. 2020Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseasescited by 6
  18. 2019Heterogeneous Multi-task Metric Learning across Multiple Domainscited by 4
  19. 2019Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processingcited by 4
  20. 2017Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signalscited by 3
  21. 2019Large Margin Multi-modal Multi-task Feature Extraction for Image Classificationcited by 3
  22. 2019A Case Study of Deep-Learned Activations via Hand-Crafted Audio Featurescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2022Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Taskcited by 2
  2. 2026UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perceptioncited by 2