Can SAM Count Anything? An Empirical Study on SAM Counting

• URL: http://arxiv.org/abs/2304.10817v1
• Date: Fri, 21 Apr 2023 08:59:48 GMT
• Title: Can SAM Count Anything? An Empirical Study on SAM Counting
• Authors: Zhiheng Ma and Xiaopeng Hong and Qinnan Shangguan
• Abstract summary: We explore the use of the Segment Anything model (SAM) for the challenging task of few-shot object counting. We find that SAM's performance is unsatisfactory without further fine-tuning, particularly for small and crowded objects.
• Score: 35.42720382193184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \url{https://github.com/Vision-Intelligence-and-Robots-Group/count-anything}.

Related papers

• Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection [58.241593208031816]
  Segment Anything Model (SAM) has been proposed as a visual fundamental model, which gives strong segmentation and generalization capabilities. We propose a Multi-scale and Detail-enhanced SAM (MDSAM) for Salient Object Detection (SOD) Experimental results demonstrate the superior performance of our model on multiple SOD datasets.
  arXiv  Detail & Related papers  (2024-08-08T09:09:37Z)
• SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation [88.80792308991867]
  Segment Anything model (SAM) has shown ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation. Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains.
  arXiv  Detail & Related papers  (2024-07-23T17:47:25Z)
• Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes [18.244508068200236]
  Crowd-SAM is a framework designed to enhance SAM's performance in crowded and occluded scenes. We introduce an efficient prompt sampler (EPS) and a part-whole discrimination network (PWD-Net) to enhance mask selection and accuracy in crowded scenes. Crowd-SAM rivals state-of-the-art (SOTA) fully-supervised object detection methods on several benchmarks including CrowdHuman and CityPersons.
  arXiv  Detail & Related papers  (2024-07-16T08:00:01Z)
• Moving Object Segmentation: All You Need Is SAM (and Flow) [82.78026782967959]
  We investigate two models for combining SAM with optical flow that harness the segmentation power of SAM with the ability of flow to discover and group moving objects. In the first model, we adapt SAM to take optical flow, rather than RGB, as an input. In the second, SAM takes RGB as an input, and flow is used as a segmentation prompt. These surprisingly simple methods, without any further modifications, outperform all previous approaches by a considerable margin in both single and multi-object benchmarks.
  arXiv  Detail & Related papers  (2024-04-18T17:59:53Z)
• TinySAM: Pushing the Envelope for Efficient Segment Anything Model [76.21007576954035]
  We propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the promptable segmentation task and further reduce the computational cost.
  arXiv  Detail & Related papers  (2023-12-21T12:26:11Z)
• Boosting Segment Anything Model Towards Open-Vocabulary Learning [69.42565443181017]
  Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model. Despite SAM finding applications and adaptations in various domains, its primary limitation lies in the inability to grasp object semantics. We present Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework.
  arXiv  Detail & Related papers  (2023-12-06T17:19:00Z)
• When SAM Meets Shadow Detection [2.9324443830722973]
  We try segment anything model (SAM) on an unexplored popular task: shadow detection. Experiments show that the performance for shadow detection using SAM is not satisfactory, especially when comparing with the elaborate models.
  arXiv  Detail & Related papers  (2023-05-19T08:26:08Z)
• Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected [41.04927631258873]
  As a foundation model in the field of computer vision, SAM (Segment Anything Model) has gained attention for its impressive performance in generic object segmentation. Despite its strong capability in a wide range of zero-shot transfer tasks, it remains unknown whether SAM can detect things in challenging setups like transparent objects.
  arXiv  Detail & Related papers  (2023-04-29T15:27:57Z)
• SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More [13.047310918166762]
  We propose textbfSAM-Adapter, which incorporates domain-specific information or visual prompts into the segmentation network by using simple yet effective adapters. We can even outperform task-specific network models and achieve state-of-the-art performance in the task we tested: camouflaged object detection.
  arXiv  Detail & Related papers  (2023-04-18T17:38:54Z)
• Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection [8.476593072868056]
  SAM is a segmentation model recently released by Meta AI Research. We try to ask if SAM can address the camouflage object detection (COD) task and evaluate the performance of SAM on the COD benchmark. We also compare SAM's performance with 22 state-of-the-art COD methods.
  arXiv  Detail & Related papers  (2023-04-10T17:05:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.