n-Reference Transfer Learning for Saliency Prediction

07/09/2020
by   Yan Luo, et al.
0

Benefiting from deep learning research and large-scale datasets, saliency prediction has achieved significant success in the past decade. However, it still remains challenging to predict saliency maps on images in new domains that lack sufficient data for data-hungry models. To solve this problem, we propose a few-shot transfer learning paradigm for saliency prediction, which enables efficient transfer of knowledge learned from the existing large-scale saliency datasets to a target domain with limited labeled examples. Specifically, very few target domain examples are used as the reference to train a model with a source domain dataset such that the training process can converge to a local minimum in favor of the target domain. Then, the learned model is further fine-tuned with the reference. The proposed framework is gradient-based and model-agnostic. We conduct comprehensive experiments and ablation study on various source domain and target domain pairs. The results show that the proposed framework achieves a significant performance improvement. The code is publicly available at <https://github.com/luoyan407/n-reference>.

READ FULL TEXT
research
05/18/2020

VerifyTL: Secure and Verifiable Collaborative Transfer Learning

Getting access to labelled datasets in certain sensitive application dom...
research
05/26/2021

Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling

Since 2014 transfer learning has become the key driver for the improveme...
research
05/22/2018

Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

The focus in machine learning has branched beyond training classifiers o...
research
04/20/2023

Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition

To transfer the knowledge learned from a labeled source domain to an unl...
research
10/06/2020

Training Deep Neural Networks for Wireless Sensor Networks Using Loosely and Weakly Labeled Images

Although deep learning has achieved remarkable successes over the past y...
research
04/11/2019

Deep Transfer Learning for Single-Channel Automatic Sleep Staging with Channel Mismatch

Many sleep studies suffer from the problem of insufficient data to fully...
research
01/09/2020

Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data

Transfer learning has proven to be a successful technique to train deep ...

Please sign up or login with your details

Forgot password? Click here to reset