Papers › SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting
SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting
Ahmed Zgaren, Wassim Bouachir, Nizar Bouguila
Zero-shot counting is a subcategory of Generic Visual Object Counting, which aims to count objects from an arbitrary class in a given image. While few-shot counting relies on delivering exemplars to the model to count similar class objects, zero-shot counting automates the operation for faster processing. This paper proposes a fully automated zeroshot method outperforming both zero-shot and few-shot methods. By exploiting feature maps from a pre-trained detection-based backbone, we introduce a new Visual Embedding Module designed to generate semantic embeddings within object contextual information. These embeddings are then fed to a Self-Attention Matching Module to generate an encoded representation for the head counter. Our proposed method has outperformed recent zeroshot approaches, achieving the best Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) results of 8.89 and 35.83, respectively, on the FSC147 dataset. Additionally, our method demonstrates competitive performance compared to few-shot methods, advancing the capabilities of visual object counting in various industrial applications such as tree counting, wildlife animal counting,
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Exemplar-Free Counting | FSC147 | SAVE | MAE(test) | 8.92 | #1 of 9 | Archive leaderboard | report |
| Exemplar-Free Counting | FSC147 | SAVE | MAE(val) | 8.89 | #1 of 9 | Archive leaderboard | report |
| Exemplar-Free Counting | FSC147 | SAVE | RMSE(test) | 80.39 | #1 of 9 | Archive leaderboard | report |
| Exemplar-Free Counting | FSC147 | SAVE | RMSE(val) | 35.83 | #1 of 9 | Archive leaderboard | report |
| Few-shot Object Counting and Detection | Zero Shot Counting on FSC147 | SAVE | MAE(test) | 8.92 | #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