Object Counting with GPT-4o and GPT-5: A Comparative Study
This addresses the problem of reducing annotation needs for object counting in computer vision, though it is incremental as it applies existing LLMs to a known task.
The study tackled zero-shot object counting by using GPT-4o and GPT-5 with textual prompts, achieving performance comparable to or surpassing state-of-the-art methods on the FSC-147 dataset.
Zero-shot object counting attempts to estimate the number of object instances belonging to novel categories that the vision model performing the counting has never encountered during training. Existing methods typically require large amount of annotated data and often require visual exemplars to guide the counting process. However, large language models (LLMs) are powerful tools with remarkable reasoning and data understanding abilities, which suggest the possibility of utilizing them for counting tasks without any supervision. In this work we aim to leverage the visual capabilities of two multi-modal LLMs, GPT-4o and GPT-5, to perform object counting in a zero-shot manner using only textual prompts. We evaluate both models on the FSC-147 and CARPK datasets and provide a comparative analysis. Our findings show that the models achieve performance comparable to the state-of-the-art zero-shot approaches on FSC-147, in some cases, even surpass them.