Learning Purified Feature Representations from Task-irrelevant Labels
Not on the map. Why?
Abstract (arXiv)
Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features extracted from task-irrelevant labels when training models on small-scale datasets. Particularly, we purify feature representations by using the expression of task-irrelevant information, thus facilitating the learning process of classification. Our work is built on solid theoretical analysis and extensive experiments, which demonstrate the effectiveness of PurifiedLearning. According to the theory we proved, PurifiedLearning is model-agnostic and doesn't have any restrictions on the model needed, so it can be combined with any existing deep neural networks with ease to achieve better performance. The source code of this paper will be available in the future for reproducibility.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 22 Feb 2021.
Builds on
21 of 46 references.
References · 21
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
9 more
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
- 2017Wasserstein GANcited by 635
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
- 2015Recent Advances in Convolutional Neural Networkscited by 360
- 2018GAN Augmentation: Augmenting Training Data using Generative Adversarial Networkscited by 107
- 2015A Deeper Look at Dataset Biascited by 86
- 2014Domain-Adversarial Neural Networkscited by 78
- 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
Built on by
Citing papers per year: 2023: 2.
2 papers.