paper-with-me

홈 › Papers

SITUATE -- Synthetic Object Counting Dataset for VLM training

2026-01-26 · René Peinl, Vincent Tischler, Patrick Schröder, Christian Groth arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.00108

Code (0)

등록된 구현이 없습니다.

Tasks

Object Counting

Similar Papers 제목 키워드 기반

OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting

2026-01-20 · Michail Spanakis, Iason Oikonomidis, Antonis Argyros arxiv

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 Counting

Semantic Generative Augmentations for Few-Shot Counting

2023-10-26 · Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne

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 Counting

The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting

2026-05-18 · Corentin Dumery, Niki Amini-Naieni, Shervin Naini, Pascal Fua arxiv

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 Counting

Learning What NOT to Count

2025-04-16 · Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh

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 Counting

Domain Randomization for Object Counting

2022-02-17 · Enric Moreu, Kevin McGuinness, Diego Ortego, Noel E. O'Connor

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