Learning Transferable Features with Deep Adaptation Networks
- Mingsheng Long, Yue Cao, Jianmin Wang, Michael I. Jordan
- Computer ScienceInternational Conference on Machine Learning
- 9 February 2015
A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding.
Conditional Adversarial Domain Adaptation
- Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
- Computer ScienceNeural Information Processing Systems
- 26 May 2017
Conditional adversarial domain adaptation is presented, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions to guarantee the transferability.
Transfer Feature Learning with Joint Distribution Adaptation
- Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu
- Computer ScienceIEEE International Conference on Computer Vision
- 1 December 2013
JDA aims to jointly adapt both the marginal distribution and conditional distribution in a principled dimensionality reduction procedure, and construct new feature representation that is effective and robust for substantial distribution difference.
Deep Transfer Learning with Joint Adaptation Networks
- Mingsheng Long, Hanhua Zhu, Jianmin Wang, Michael I. Jordan
- Computer ScienceInternational Conference on Machine Learning
- 21 May 2016
JAN is presented, which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion.
HashNet: Deep Learning to Hash by Continuation
- Zhangjie Cao, Mingsheng Long, Jianmin Wang, Philip S. Yu
- Computer ScienceIEEE International Conference on Computer Vision
- 2 February 2017
HashNet is presented, a novel deep architecture for deep learning to hash by continuation method with convergence guarantees, which learns exactly binary hash codes from imbalanced similarity data.
Unsupervised Domain Adaptation with Residual Transfer Networks
- Mingsheng Long, Hanjing Zhu, Jianmin Wang, Michael I. Jordan
- Computer ScienceNIPS
- 14 February 2016
Empirical evidence shows that the new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeledData in the target domain outperforms state of the art methods on standard domain adaptation benchmarks.
Transfer Joint Matching for Unsupervised Domain Adaptation
- Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 23 June 2014
This paper aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances.
Deep Hashing Network for Efficient Similarity Retrieval
- Han Zhu, Mingsheng Long, Jianmin Wang, Yue Cao
- Computer ScienceAAAI Conference on Artificial Intelligence
- 12 February 2016
A novel Deep Hashing Network (DHN) architecture for supervised hashing is proposed, in which good image representation tailored to hash coding and formally control the quantization error are jointly learned.
Partial Adversarial Domain Adaptation
- Zhangjie Cao, Li-jie Ma, Mingsheng Long, Jianmin Wang
- Computer ScienceEuropean Conference on Computer Vision
- 10 August 2018
This paper presents Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space.
Bridging Theory and Algorithm for Domain Adaptation
- Yuchen Zhang, Tianle Liu, Mingsheng Long, Michael I. Jordan
- Computer ScienceInternational Conference on Machine Learning
- 11 April 2019
Margin Disparity Discrepancy is introduced, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training.
...
...