SITUATE -- Synthetic Object Counting Dataset for VLM training
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Object CountingSimilar Papers 제목 키워드 기반
OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting
Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing me…
Object CountingSemantic Generative Augmentations for Few-Shot Counting
With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works show that it can effectively augment or eve…
Diversityimage-classificationImage ClassificationObject CountingThe MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mixed-object setting that dominates real-world applications such as ind…
Object CountingLearning What NOT to Count
Few/zero-shot object counting methods reduce the need for extensive annotations but often struggle to distinguish between fine-grained categories, especially when multiple similar objects appear in the same scene. To add…
Object CountingZero-Shot CountingDomain Randomization for Object Counting
Recently, the use of synthetic datasets based on game engines has been shown to improve the performance of several tasks in computer vision. However, these datasets are typically only appropriate for the specific domains…
ObjectObject Counting