Distant Domain Transfer Learning

By Ben Tan, Yu Zhang, Sinno Jialin Pan, Qiang Yang. 2017

202 citations recorded by the source corpus.

In this paper, we study a novel transfer learning problem termed Distant Domain Transfer Learning (DDTL). Different from existing transfer learning problems which assume that there is a close relation between the source domain and the target domain, in the DDTL problem, the target domain can be totally different from the source domain. For example, the source domain classifies face images but the target domain distinguishes plane images. Inspired by the cognitive processof human where two seemingly unrelated concepts can be connected by learning intermediate concepts gradually, we propose a Selective Learning Algorithm (SLA) to solve the DDTL problem with supervised autoencoder or supervised convolutional autoencoder as a base model for handling different types of inputs. Intuitively, the SLA algorithm selects usefully unlabeled data gradually from intermediate domains as a bridge to break the large distribution gap for transferring knowledge between two distant domains. Empirical studies on image classification problems demonstrate the effectiveness of the proposed algorithm, and on some tasks the improvement in terms of the classification accuracy is up to 17% over “non-transfer” methods.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jindong Wang
2. Wai Lam
3. Lidong Bing
4. Yiqiang Chen
5. Dongrui Wu
6. Mei Wang
7. Lingfei Deng
8. Wen Zhang

Citations in the corpus

• Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2019, background): “Transfer learning (Pan and Yang, 2009; Tan et al., 2017) refers to a broad scope of methods that exploit knowledge cross domains for handling tasks in the target domain.”
• Overcoming Negative Transfer: A Survey (2020, background): “Feature, pseudo label noise [13], [90]–[92] Transitive Transfer [93]–[95]”
• Stratified Transfer Learning for Cross-domain Activity Recognition (2017, methodology): “Instance-based methods perform knowledge transfer mainly through instance re-weighting techniques [26], [27].”
• Deep Visual Domain Adaptation: A Survey (2018, methodology): “[92] proposed distant domain transfer learning (DDTL), where long-distance domains fail to transfer knowledge by only one intermediate domain but can be related via multiple intermediate domains.”
• A Decade Survey of Transfer Learning (2010–2020) (2020, methodology): “Similarly, another instance-based algorithm was introduced by [63].”
• Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation (2019, background): “Domain adaptation is a class of techniques that aims to reduce the discrepancy between different domains (Tan et al. 2017).”
• A Survey on Negative Transfer (2020, background): “[51] introduced an instance selection mechanism to identify useful source data, and constructs multiple intermediate domains.”