</> Code with Papers by Syntology

Papers › n-Reference Transfer Learning for Saliency Prediction

n-Reference Transfer Learning for Saliency Prediction

9 Jul 2020arXiv:2007.05104archive 2025-07-28

Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

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 \url{https://github.com/luoyan407/n-reference}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

luoyan407/n-reference mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Transfer Learning for Saliency PredictionPredictionSaliency PredictionTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot DINet+FT|Ref AUC 0.8051 #1 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot DINet+FT|Ref CC 0.6121 #1 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot DINet+FT|Ref NSS 1.5077 #1 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot ResNet+FT|Ref AUC 0.7983 #2 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot ResNet+FT|Ref CC 0.5817 #2 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 1-shot ResNet+FT|Ref NSS 1.4272 #2 of 2 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 10-shot DINet+FT|Ref AUC 0.8276 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 10-shot DINet+FT|Ref CC 0.6605 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 10-shot DINet+FT|Ref NSS 1.6439 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 5-shot DINet+FT|Ref AUC 0.8200 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 5-shot DINet+FT|Ref CC 0.6468 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - 5-shot DINet+FT|Ref NSS 1.6085 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - EUB DINet+FT|Ref AUC 0.8494 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - EUB DINet+FT|Ref CC 0.7442 #1 of 1 Archive leaderboard report
Few-Shot Transfer Learning for Saliency Prediction SALICON->WebpageSaliency - EUB DINet+FT|Ref NSS 1.8831 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections