Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively

• URL: http://arxiv.org/abs/2401.02955v2
• Date: Sat, 14 Sep 2024 00:26:00 GMT
• Title: Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
• Authors: Haobo Yuan, Xiangtai Li, Chong Zhou, Yining Li, Kai Chen, Chen Change Loy,
• Abstract summary: The Open-Vocabulary SAM is a SAM-inspired model designed for simultaneous interactive segmentation and recognition. Our method can segment and recognize approximately 22,000 classes.
• Score: 69.97238935096094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the na\"{i}ve baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes.

Related papers

• SAM-SP: Self-Prompting Makes SAM Great Again [11.109389094334894]
  Segment Anything Model (SAM) has demonstrated impressive capabilities in zero-shot segmentation tasks. SAM encounters noticeably degradation performance when applied to specific domains, such as medical images. We introduce a novel self-prompting based fine-tuning approach, called SAM-SP, tailored for extending the vanilla SAM model.
  arXiv  Detail & Related papers  (2024-08-22T13:03:05Z)
• 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)
• AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning [61.666973416903005]
  Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. We propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context.
  arXiv  Detail & Related papers  (2024-06-01T16:21:39Z)
• PosSAM: Panoptic Open-vocabulary Segment Anything [58.72494640363136]
  PosSAM is an open-vocabulary panoptic segmentation model that unifies the strengths of the Segment Anything Model (SAM) with the vision-native CLIP model in an end-to-end framework. We introduce a Mask-Aware Selective Ensembling (MASE) algorithm that adaptively enhances the quality of generated masks and boosts the performance of open-vocabulary classification during inference for each image.
  arXiv  Detail & Related papers  (2024-03-14T17:55:03Z)
• ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [5.376142948115328]
  We propose a CLIP and SAM collaboration framework called ClipSAM for ZSAS. The insight behind ClipSAM is to employ CLIP's semantic understanding capability for anomaly localization and rough segmentation. In details, we introduce a crucial Unified Multi-scale Cross-modal Interaction (UMCI) module for interacting with visual features.
  arXiv  Detail & Related papers  (2024-01-23T11:20:03Z)
• 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)
• SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding [40.40630116715132]
  The landscape of publicly available vision foundation models (VFMs) is expanding rapidly. We introduce a simple recipe to efficiently merge VFMs into a unified model that absorbs their expertise. By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
  arXiv  Detail & Related papers  (2023-10-23T19:21:57Z)
• Semantic-SAM: Segment and Recognize Anything at Any Granularity [83.64686655044765]
  We introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. We consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts. For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels.
  arXiv  Detail & Related papers  (2023-07-10T17:59:40Z)

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.