SITUATE -- Synthetic Object Counting Dataset for VLM training
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914296341987328 |
|---|---|
| author | Peinl, René Tischler, Vincent Schröder, Patrick Groth, Christian |
| author_facet | Peinl, René Tischler, Vincent Schröder, Patrick Groth, Christian |
| contents | We present SITUATE, a novel dataset designed for training and evaluating Vision Language Models on counting tasks with spatial constraints. The dataset bridges the gap between simple 2D datasets like VLMCountBench and often ambiguous real-life datasets like TallyQA, which lack control over occlusions and spatial composition. Experiments show that our dataset helps to improve generalization for out-of-distribution images, since a finetune of Qwen VL 2.5 7B on SITUATE improves accuracy on the Pixmo count test data, but not vice versa. We cross validate this by comparing the model performance across established other counting benchmarks and against an equally sized fine-tuning set derived from Pixmo count. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00108 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SITUATE -- Synthetic Object Counting Dataset for VLM training Peinl, René Tischler, Vincent Schröder, Patrick Groth, Christian Computer Vision and Pattern Recognition Artificial Intelligence I.2.10 We present SITUATE, a novel dataset designed for training and evaluating Vision Language Models on counting tasks with spatial constraints. The dataset bridges the gap between simple 2D datasets like VLMCountBench and often ambiguous real-life datasets like TallyQA, which lack control over occlusions and spatial composition. Experiments show that our dataset helps to improve generalization for out-of-distribution images, since a finetune of Qwen VL 2.5 7B on SITUATE improves accuracy on the Pixmo count test data, but not vice versa. We cross validate this by comparing the model performance across established other counting benchmarks and against an equally sized fine-tuning set derived from Pixmo count. |
| title | SITUATE -- Synthetic Object Counting Dataset for VLM training |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.2.10 |
| url | https://arxiv.org/abs/2602.00108 |