Label Efficient Learning of Transferable Representations acrosss Domains and Tasks
نویسندگان
چکیده
Fine-tuned matching net 0.645±0.019 0.755±0.024 0.793±0.013 0.827±0.011 Ours: fine-tune + adv. 0.702±0.020 0.800±0.013 0.804±0.014 0.831±0.013 Ours: full model 0.917±0.007 0.936±0.006 0.942±0.006 0.950±0.004 Label-Efficient Learning of Transferable Representations across Domains and Tasks Zelun Luo1, Yuliang Zou2, Judy Hoffman3, Li Fei-Fei1 1 Stanford University 2 Virginia Tech 3 University of California, Berkeley
منابع مشابه
Label Efficient Learning of Transferable Representations across Domains and Tasks
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target doma...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملProactive Transfer Learning for Heterogeneous Feature and Label Spaces
We propose a framework for learning new target tasks by leveraging existing heterogeneous knowledge sources. Unlike the traditional transfer learning, we do not require explicit relations between source and target tasks, and instead let the learner actively mine transferable knowledge from a source dataset. To this end, we develop (1) a transfer learning method for source datasets with heteroge...
متن کاملImage Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کاملOn the Limits of Learning Representations with Label-Based Supervision
Advances in neural network based classifiers have accelerated the progress of automatic representation learning. Since the emergence of AlexNet (Krizhevsky et al., 2012), every winning submission of the ImageNet challenge (Russakovsky et al., 2015) has employed end-to-end representation learning, and due to the utility of good representations for transfer learning (Yosinski et al., 2014), repre...
متن کامل