Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels
Not on the map. Why?
Abstract (arXiv)
In real-world scenarios we often need to perform multiple tasks simultaneously. Multi-Task Learning (MTL) is an adequate method to do so, but usually requires datasets labeled for all tasks. We propose a method that can leverage datasets labeled for only some of the tasks in the MTL framework. Our work, Knowledge Assembly (KA), learns multiple tasks from disjoint datasets by leveraging the unlabeled data in a semi-supervised manner, using model augmentation for pseudo-supervision. Whilst KA can be implemented on any existing MTL networks, we test our method on jointly learning person re-identification (reID) and pedestrian attribute recognition (PAR). We surpass the single task fully-supervised performance by 4.2% points for reID and 0.9% points for PAR.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 15 Jun 2023.
Builds on
24 of 30 references.
References · 24
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
- 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
- 2017A Survey on Multi-Task Learningcited by 838
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
- 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
- 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
12 more
- 2020An Overview of Deep Semi-Supervised Learningcited by 121
- 2017Improving Person Re-identification by Attribute and Identity Learningcited by 95
- 2017HydraPlus-Net: Attentive Deep Features for Pedestrian Analysiscited by 89
- 2020Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contextscited by 51
- 2021When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Frameworkcited by 29
- 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
- 2022Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structurescited by 18
- 2018Disjoint Multi-task Learning between Heterogeneous Human-centric Taskscited by 16
- 2020Partly Supervised Multitask Learningcited by 11
- 2022UPAR: Unified Pedestrian Attribute Recognition and Person Retrievalcited by 10
- 2020Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasetscited by 4
- 2021EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Imagescited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.