Browse State-of-the-Art › Few-Shot Transfer Learning for Saliency Prediction
Few-Shot Transfer Learning for Saliency Prediction
1 paper with code · 4 benchmarks · 1 dataset archive 2025-07-28
Saliency prediction aims to predict important locations in a visual scene. It is a per-pixel regression task with predicted values ranging from 0 to 1.
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.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| SALICON->WebpageSaliency - 1-shot (2 rows) | DINet+FT|Ref | n-Reference Transfer Learning for Saliency Prediction | code | — | Compare |
| SALICON->WebpageSaliency - 5-shot (1 row) | DINet+FT|Ref | n-Reference Transfer Learning for Saliency Prediction | code | — | Compare |
| SALICON->WebpageSaliency - 10-shot (1 row) | DINet+FT|Ref | n-Reference Transfer Learning for Saliency Prediction | code | — | Compare |
| SALICON->WebpageSaliency - EUB (1 row) | DINet+FT|Ref | n-Reference Transfer Learning for Saliency Prediction | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Most implemented papers archive 2025-07-28
1 shown of 1 paper with code (1 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
9 Jul 2020 1 repository listedThe proposed framework is gradient-based and model-agnostic.
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