Research map / Detection and segmentation / Open-set and few-shot detection
Benchmarking Dense and Indiscernible Object Counting with Blueberries
Weihao Bo, Yanpeng Sun, Jingwen Qin, Fei Shen, Xiaofan Li, Zechao Li
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 CLIP-based mask generation (ablation) | vanilla model · DIOCblueberry | MAE: 7.14 -> 7.02 | Improved |
| add CLIP-based mask generation (ablation) | vanilla model · DIOCblueberry | RMSE: 14.44 -> 12.28 | Improved |
| add contrastive loss (ablation) | VM+Mask · DIOCblueberry | MAE: 7.02 -> 6.94 | Improved |
| add contrastive loss (ablation) | VM+Mask · DIOCblueberry | RMSE: 12.28 -> 10.44 | Improved |
| add edge-aware patch cropping (ablation) | VM+Mask+Con · DIOCblueberry | MAE: 6.94 -> 3.63 | Improved |
| add edge-aware patch cropping (ablation) | VM+Mask+Con · DIOCblueberry | RMSE: 10.44 -> 4.26 | Improved |
| use edge-aware cropping instead of general crop (ablation) | MaskCount · DIOCblueberry | MAE: 6.36 -> 3.63 | Improved |
| use CLIP ViT-B/16 instead of SLIP ViT-B/16 (ablation) | MaskCount · DIOCblueberry | MAE: 5.78 -> 3.63 | Improved |
| use CLIP ViT-B/16 instead of CLIP ViT-B/32 (ablation) | MaskCount · DIOCblueberry | MAE: 7.04 -> 3.63 | Improved |
| use proposed contrastive loss instead of InfoNCE (ablation) | MaskCount · DIOCblueberry | MAE: 5.20 -> 3.63 | Improved |
| use proposed contrastive loss instead of sigmoid similarity loss (ablation) | MaskCount · DIOCblueberry | MAE: 6.63 -> 3.63 | Improved |
| use MaskCount instead of CounTR | CounTR · DIOCblueberry | MAE: 67.02 -> 3.63 | Improved |
Closest papers by meaning
- Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes (CVPR 2024 · similarity 0.87)
- Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind (NeurIPS 2025 · similarity 0.85)
- DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting (CVPR 2024 · similarity 0.84)
- OmniCount: Multi-label Object Counting with Semantic-Geometric Priors (AAAI 2025 · similarity 0.84)
- See What We Cannot See: A Geo-guided Reasoning Benchmark for Object Counting under Adverse Earth Observation Conditions (CVPR 2026 · similarity 0.84)
- COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition (NeurIPS 2026 · similarity 0.83)
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.
