What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation

By Jiahua Dong, Yang Cong, Gan Sun, Bineng Zhong, Xiaowei Xu. 2020

149 citations recorded by the source corpus.

Unsupervised domain adaptation has attracted growing research attention on semantic segmentation. However, 1) most existing models cannot be directly applied into lesions transfer of medical images, due to the diverse appearances of same lesion among different datasets; 2) equal attention has been paid into all semantic representations instead of neglecting irrelevant knowledge, which leads to negative transfer of untransferable knowledge. To address these challenges, we develop a new unsupervised semantic transfer model including two complementary modules (i.e., T_D and T_F ) for endoscopic lesions segmentation, which can alternatively determine where and how to explore transferable domain-invariant knowledge between labeled source lesions dataset (e.g., gastroscope) and unlabeled target diseases dataset (e.g., enteroscopy). Specifically, T_D focuses on where to translate transferable visual information of medical lesions via residual transferability-aware bottleneck, while neglecting untransferable visual characterizations. Furthermore, T_F highlights how to augment transferable semantic features of various lesions and automatically ignore untransferable representations, which explores domain-invariant knowledge and in return improves the performance of T_D. To the end, theoretical analysis and extensive experiments on medical endoscopic dataset and several non-medical public datasets well demonstrate the superiority of our proposed model.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

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. Wen Li
2. Yahao Liu
3. Jinhong Deng
4. Lixin Duan
5. Tong Chu
6. Zhen Fang
7. Jie Lu
8. Bo Xu

In Computer Vision and Pattern Recognition

1. Wen Li
2. Yahao Liu
3. Jinhong Deng
4. Lixin Duan
5. Tong Chu
6. Luc Van Gool
7. Zhen Fang
8. Feng Liu

In Radiology, Nuclear Medicine and Imaging

1. Zhen Fang
2. Jinhong Deng
3. Yixuan Li
4. Lixin Duan
5. Yahao Liu
6. Zhengming Ding
7. Feng Liu
8. Wen Li

Citations in the corpus

• Federated Class-Incremental Learning (2022, background): “, autonomous driving [39], wearable devices [33], medical diagnosis [10, 52] and mobile phones [36].”
• HGNet: Hybrid Generative Network for Zero-Shot Domain Adaptation (2020, background): “However, domain adaptation provides an alternative strategy to handle with such a problem [24, 9, 28].”
• Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization (2021, background): “Intuitively, NTL goes against the current research trend of improving the generalization ability of models across various domains, e.g., domain generalization and adaptation (Zhou et al., 2020; Dong et al., 2020).”
• Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation (2022, methodology): “Recently, selfsupervised methods, including self-training [16, 17, 32, 49, 51, 52, 54, 55] and semantic consistency [26, 41, 47], have been shown to significantly improve the cross-domain semantic segmentation performance.”
• VLP: A Survey on Vision-language Pre-training (2022, background): “Recently, VDBERT [134] models the common implicit vision-language alignment in vision and language by pretraining on large-scale image-text pairs via transfer learning [135, 136].”
• Addressing Class Imbalance in Federated Learning (2020, background): “In the case where they have significant differences, transfer learning techniques such as domain adaptation (Ganin and Lempitsky 2015; Dong et al. 2020; Xu et al. 2021) may be needed to reduce the distribution discrepancy of different clients.”
• I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting (2020, background): “…al. 2020), intelligent robotics (Stria and Hlavc 2018; Wei, Deng, and Yang 2020; Chen et al. 2020), object clustering (Yang et al. 2020; Zhang et al. 2020a, 2021), medical diagnosis (Dong et al. 2019, 2020b), transfer learning (Dong et al. 2020a; Fang ∗The corresponding author is Prof. Yang Cong.”
• Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation (2022, methodology): “While many methods have been proposed to solve the UDA problem (Ganin and Lempitsky 2015; Long et al. 2018; Saito et al. 2018; Dong et al. 2020; Liu et al. 2021; Deng et al. 2021; Dong et al. 2021), these approaches is needed to access the source domain data during the training process.”
• Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation (2021, methodology): “In generative adversarial network based domain adaptation, as introduced in [12], the discriminator could assist in distinguishing the cross-domain semantic knowledge that is trans-ferable or untransferable, by identifying whether a given sample is from source or target domain (i.e., domain…”
• Is Out-of-Distribution Detection Learnable? (2022, methodology): “[80] Jiahua Dong, Yang Cong, Gan Sun, Bineng Zhong, and Xiaowei Xu.”
• Learning Bounds for Open-Set Learning (2021, methodology): “Based on this fact, we aim to establish the OSL theory from transfer learning (Dong et al., 2019; 2020a;b; 2021; Liu et al., 2019; Lu et al., 2015; Luo et al., 2020a; Niu et al., 2020; Pan & Yang, 2010; Wang et al., 2020), which learns knowledge for a given domain from a different, but relative…”