Deep Representation Learning with Target Coding
By Shuo Yang, Ping Luo, Chen Change Loy, Kenneth W. Shum, Xiaoou Tang. 2015
68 citations recorded by the source corpus.
We consider the problem of learning deep representation when target labels are available. In this paper, we show that there exists intrinsic relationship between target coding and feature representation learning in deep networks. Specifically, we found that distributed binary acode with error correcting capability is more capable of encouraging discriminative features, in comparison tothe 1-of-K coding that is typically used in supervised deep learning. This new finding reveals additional benefit of using error-correcting code for deep model learning,apart from its well-known error correcting property. Extensive experiments are conducted on popular visual benchmark datasets.
Subfields: Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Pau Rodr'iguez L'opez
- Miguel Angel Bautista
- Bo-Hao Chang
- Eldad Haber
- David Begert
- Lili Meng
- Jordi Gonzàlez
- Lars Ruthotto
Citations in the corpus
- Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “TextTopicNet (Wiki) - CNN-finetuning * 76.51% TextTopicNet (Wiki) - fc7+SVM * 66.00% Semi-supervised auto-encoder [44] 74.33 % Convolutional k-means [8] 74.10% CNN with Target Coding [43] 73.15% Exemplar convnets [7] 72.80% Unsupervised pre-training [26] 70.20% Swersky et al .”
- Supervised Contrastive Learning (2020, neutral): “1 [57] Shuo Yang, Ping Luo, Chen Change Loy, Kenneth W Shum, and Xiaoou Tang.”
- Beyond One-hot Encoding: lower dimensional target embedding (2018, methodology): “But due to the efficiency of data-dependent codes, our encoding proposal is shown more efficient than [48], by halving the required CNN output size, and eliminating the need of training multiple CNNs to predict code chunks.”
- Reversible Architectures for Arbitrarily Deep Residual Neural Networks (2017, methodology): “We use three state-of-the-art methods as baselines for the STL-10 dataset: Deep Representation Learning (Yang et al. 2015), Convolutional Clustering (Dundar, Jin, and Culurciello 2015), and Stacked what-where auto-encoders (Zhao et al.”