FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
- URL: http://arxiv.org/abs/2409.03525v1
- Date: Thu, 5 Sep 2024 13:36:50 GMT
- Title: FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
- Authors: Xi Chen, Haosen Yang, Sheng Jin, Xiatian Zhu, Hongxun Yao,
- Abstract summary: FrozenSeg is designed to integrate spatial knowledge from a localization foundation model (e.g., SAM) and semantic knowledge extracted from a ViL model (e.g., CLIP)
FrozenSeg advances state-of-the-art results across various segmentation benchmarks, trained exclusively on COCO panoptic data, and tested in a zero-shot manner.
- Score: 47.0028071183214
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Open-vocabulary segmentation poses significant challenges, as it requires segmenting and recognizing objects across an open set of categories in unconstrained environments. Building on the success of powerful vision-language (ViL) foundation models, such as CLIP, recent efforts sought to harness their zero-short capabilities to recognize unseen categories. Despite notable performance improvements, these models still encounter the critical issue of generating precise mask proposals for unseen categories and scenarios, resulting in inferior segmentation performance eventually. To address this challenge, we introduce a novel approach, FrozenSeg, designed to integrate spatial knowledge from a localization foundation model (e.g., SAM) and semantic knowledge extracted from a ViL model (e.g., CLIP), in a synergistic framework. Taking the ViL model's visual encoder as the feature backbone, we inject the space-aware feature into the learnable queries and CLIP features within the transformer decoder. In addition, we devise a mask proposal ensemble strategy for further improving the recall rate and mask quality. To fully exploit pre-trained knowledge while minimizing training overhead, we freeze both foundation models, focusing optimization efforts solely on a lightweight transformer decoder for mask proposal generation-the performance bottleneck. Extensive experiments demonstrate that FrozenSeg advances state-of-the-art results across various segmentation benchmarks, trained exclusively on COCO panoptic data, and tested in a zero-shot manner. Code is available at https://github.com/chenxi52/FrozenSeg.
Related papers
- Adapting Vision-Language Model with Fine-grained Semantics for Open-Vocabulary Segmentation [42.020470627552136]
Open-vocabulary segmentation is primarily bottlenecked by mask classification, not mask generation.
We propose a novel Fine-grained Semantic Adaptation (FISA) method to address this limitation.
FISA enhances the extracted visual features with fine-grained semantic awareness by explicitly integrating this crucial semantic information early in the visual encoding process.
arXiv Detail & Related papers (2024-09-24T17:50:28Z) - 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) - CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation [25.557135220449236]
We propose a learnable augmentation method for camouflaged object detection (COD) and camouflaged instance segmentation (CIS)
Our proposed augmentation method boosts the performance of camouflaged object detectors and instance segmenters by large margins.
arXiv Detail & Related papers (2023-08-29T22:43:46Z) - RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation.
Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal.
We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
arXiv Detail & Related papers (2023-07-03T13:21:58Z) - Fine-Grained Visual Prompting [35.032567257651515]
Fine-Grained Visual Prompting (FGVP) demonstrates superior performance in zero-shot comprehension of referring expressions.
It outperforms prior methods by an average margin of 3.0% to 4.6%, with a maximum improvement of 12.5% on the RefCOCO+ testA subset.
arXiv Detail & Related papers (2023-06-07T11:39:56Z) - Global Knowledge Calibration for Fast Open-Vocabulary Segmentation [124.74256749281625]
We introduce a text diversification strategy that generates a set of synonyms for each training category.
We also employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP.
Our proposed model achieves robust generalization performance across various datasets.
arXiv Detail & Related papers (2023-03-16T09:51:41Z) - A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained
Vision-language Model [61.58071099082296]
It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation.
In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP.
Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
arXiv Detail & Related papers (2021-12-29T18:56:18Z) - Novel Class Discovery in Semantic Segmentation [104.30729847367104]
We introduce a new setting of Novel Class Discovery in Semantic (NCDSS)
It aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image.
We propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels.
arXiv Detail & Related papers (2021-12-03T13:31:59Z)
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.