Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation

• URL: http://arxiv.org/abs/2207.08549v1
• Date: Mon, 18 Jul 2022 12:12:42 GMT
• Title: Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
• Authors: Xinyu Shi, Dong Wei, Yu Zhang, Donghuan Lu, Munan Ning, Jiashun Chen, Kai Ma, and Yefeng Zheng
• Abstract summary: Few-shot Semantic Dense (FSS) has attracted great attention. The goal of FSS is to segment target objects in a query image given only a few annotated support images of the target class. We propose pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (AMADC), where both foreground and background support information are fully exploited.
• Score: 25.605580031284052
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. In this paper, we propose Dense pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (DCAMA), where both foreground and background support information are fully exploited via multi-level pixel-wise correlations between paired query and support features. Implemented with the scaled dot-product attention in the Transformer architecture, DCAMA treats every query pixel as a token, computes its similarities with all support pixels, and predicts its segmentation label as an additive aggregation of all the support pixels' labels -- weighted by the similarities. Based on the unique formulation of DCAMA, we further propose efficient and effective one-pass inference for n-shot segmentation, where pixels of all support images are collected for the mask aggregation at once. Experiments show that our DCAMA significantly advances the state of the art on standard FSS benchmarks of PASCAL-5i, COCO-20i, and FSS-1000, e.g., with 3.1%, 9.7%, and 3.6% absolute improvements in 1-shot mIoU over previous best records. Ablative studies also verify the design DCAMA.

Related papers

• FCC: Fully Connected Correlation for Few-Shot Segmentation [11.277022867553658]
  Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer features. We introduce FCC (Fully Connected Correlation) to integrate pixel-level correlations between support and query features.
  arXiv  Detail & Related papers  (2024-11-18T03:32:02Z)
• Group-On: Boosting One-Shot Segmentation with Supportive Query [8.623405412540247]
  One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class. We propose a novel approach for ONE-shot semantic segmentation, called Group-On, which packs multiple query images in batches.
  arXiv  Detail & Related papers  (2024-04-18T03:10:04Z)
• Dense Affinity Matching for Few-Shot Segmentation [83.65203917246745]
  Few-Shot (FSS) aims to segment the novel class images with a few samples. We propose a dense affinity matching framework to exploit the support-query interaction. We show that our framework performs very competitively under different settings with only 0.68M parameters.
  arXiv  Detail & Related papers  (2023-07-17T12:27:15Z)
• Holistic Prototype Attention Network for Few-Shot VOS [74.25124421163542]
  Few-shot video object segmentation (FSVOS) aims to segment dynamic objects of unseen classes by resorting to a small set of support images. We propose a holistic prototype attention network (HPAN) for advancing FSVOS.
  arXiv  Detail & Related papers  (2023-07-16T03:48:57Z)
• Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation [63.910211095033596]
  Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. We propose a simple yet versatile framework in the spirit of divide-and-conquer. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information.
  arXiv  Detail & Related papers  (2022-04-21T06:21:14Z)
• Few-shot Segmentation with Optimal Transport Matching and Message Flow [50.9853556696858]
  It is essential for few-shot semantic segmentation to fully utilize the support information. We propose a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module. Experiments on PASCAL VOC 2012, MS COCO, and FSS-1000 datasets show that our network achieves new state-of-the-art few-shot segmentation performance.
  arXiv  Detail & Related papers  (2021-08-19T06:26:11Z)
• Few-Shot Segmentation with Global and Local Contrastive Learning [51.677179037590356]
  We propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning. We generate the prior region maps for query images, which locate the objects, as guidance to perform cross interaction with support features. Without bells and whistles, the proposed approach achieves new state-of-the-art performance for the few-shot segmentation task.
  arXiv  Detail & Related papers  (2021-08-11T15:52:22Z)
• Few-Shot Segmentation via Cycle-Consistent Transformer [74.49307213431952]
  We focus on utilizing pixel-wise relationships between support and target images to facilitate the few-shot semantic segmentation task. We propose using a novel cycle-consistent attention mechanism to filter out possible harmful support features. Our proposed CyCTR leads to remarkable improvement compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-04T07:57:48Z)
• Self-Guided and Cross-Guided Learning for Few-Shot Segmentation [12.899804391102435]
  We propose a self-guided learning approach for few-shot segmentation. By making an initial prediction for the annotated support image, the covered and uncovered foreground regions are encoded to the primary and auxiliary support vectors. By aggregating both primary and auxiliary support vectors, better segmentation performances are obtained on query images.
  arXiv  Detail & Related papers  (2021-03-30T07:36:41Z)

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.