Research map / Detection and segmentation / Open-set and few-shot detection
Class-Agnostic Object Counting Robust to Intraclass Diversity
Shenjian Gong, Shanshan Zhang, Jian Yang, Dengxin Dai, Bernt Schiele
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add exemplar feature augmentation (ablation) | FamNet* · FSC-147 val | MAE: 24.32 -> 23.08 | Improved |
| add edge matching (ablation) | FamNet* · FSC-147 val | MAE: 24.32 -> 23.29 | Improved |
| add both exemplar feature augmentation and edge matching (ablation) | FamNet* · FSC-147 val | MAE: 24.32 -> 20.54 | Improved |
| add exemplar feature augmentation (ablation) | FamNet* · FSC-147 val, color-diversity subset | MAE: 42.32 -> 38.43 | Improved |
| add edge matching (ablation) | FamNet* · FSC-147 val, color-diversity subset | MAE: 42.32 -> 35.84 | Improved |
| add exemplar feature augmentation (ablation) | FamNet* · FSC-147 val, scale-diversity subset | MAE: 42.65 -> 38.95 | Improved |
| add edge matching (ablation) | FamNet* · FSC-147 val, scale-diversity subset | MAE: 42.65 -> 39.09 | Improved |
| use Dirichlet theta {2,2,2} instead of uneven {3,2,2} (ablation) | RCAC · FSC-147 val | MAE: 21.44 -> 20.54 | Improved |
| use Dirichlet theta {5,5,5} instead of {2,2,2} (ablation) | RCAC · FSC-147 val | MAE: 20.54 -> 20.46 | Mixed |
| increase augmented features N from 0 to 7 (ablation) | RCAC · FSC-147 val | MAE: 23.29 -> 20.54 | Improved |
| replace Sobel with RCF edge detector (ablation) | RCAC · FSC-147 val | MAE: 22.41 -> 20.94 | Improved |
| use RCAC instead of FamNet | FamNet · FSC-147 test | MAE: 22.08 -> 20.21 | Improved |
Closest papers by meaning
- Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting (AAAI 2024 · similarity 0.89)
- Point Segment and Count: A Generalized Framework for Object Counting (CVPR 2024 · similarity 0.87)
- PBECount: Prompt-Before-Extract Paradigm for Class-Agnostic Counting (AAAI 2025 · similarity 0.87)
- A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation (NeurIPS 2024 · similarity 0.87)
- DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting (CVPR 2024 · similarity 0.86)
- OmniCount: Multi-label Object Counting with Semantic-Geometric Priors (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
