Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Eliminating Feature Ambiguity for Few-Shot Segmentation

Qianxiong Xu, Guosheng Lin, Chen Change Loy, Cheng Long, Ziyue Li, Rui Zhao

TL;DR

The paper provides comprehensive ECCV submission guidelines, focusing on formatting, anonymity, and submission workflows. It prescribes English-language manuscripts, official LNCS templates, and LaTeX usage with line numbers for review, with a Word alternative available. It outlines page limits (14 pages for review excluding references), the necessity of a paper ID, and line-numbering rules, alongside policies on confidentiality and double-blind review. It also details figure, equation, and citation formatting, and notes that camera-ready preparation details follow decision announcements. Overall, the document standardizes submissions to ensure a fair, uniform review process and reliable public archival formatting.

Abstract

Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. However, due to the large receptive fields in deep layers of the backbone, the extracted query and support FG features are inevitably mingled with background (BG) features, impeding the FG-FG matching in cross attention. Hence, the query FG features are fused with less support FG features, i.e., the support information is not well utilized. This paper presents a novel plug-in termed ambiguity elimination network (AENet), which can be plugged into any existing cross attention-based FSS methods. The main idea is to mine discriminative query FG regions to rectify the ambiguous FG features, increasing the proportion of FG information, so as to suppress the negative impacts of the doped BG features. In this way, the FG-FG matching is naturally enhanced. We plug AENet into three baselines CyCTR, SCCAN and HDMNet for evaluation, and their scores are improved by large margins, e.g., the 1-shot performance of SCCAN can be improved by 3.0%+ on both PASCAL-5$^i$ and COCO-20$^i$. The code is available at https://github.com/Sam1224/AENet.

Eliminating Feature Ambiguity for Few-Shot Segmentation

TL;DR

The paper provides comprehensive ECCV submission guidelines, focusing on formatting, anonymity, and submission workflows. It prescribes English-language manuscripts, official LNCS templates, and LaTeX usage with line numbers for review, with a Word alternative available. It outlines page limits (14 pages for review excluding references), the necessity of a paper ID, and line-numbering rules, alongside policies on confidentiality and double-blind review. It also details figure, equation, and citation formatting, and notes that camera-ready preparation details follow decision announcements. Overall, the document standardizes submissions to ensure a fair, uniform review process and reliable public archival formatting.

Abstract

Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. However, due to the large receptive fields in deep layers of the backbone, the extracted query and support FG features are inevitably mingled with background (BG) features, impeding the FG-FG matching in cross attention. Hence, the query FG features are fused with less support FG features, i.e., the support information is not well utilized. This paper presents a novel plug-in termed ambiguity elimination network (AENet), which can be plugged into any existing cross attention-based FSS methods. The main idea is to mine discriminative query FG regions to rectify the ambiguous FG features, increasing the proportion of FG information, so as to suppress the negative impacts of the doped BG features. In this way, the FG-FG matching is naturally enhanced. We plug AENet into three baselines CyCTR, SCCAN and HDMNet for evaluation, and their scores are improved by large margins, e.g., the 1-shot performance of SCCAN can be improved by 3.0%+ on both PASCAL-5 and COCO-20. The code is available at https://github.com/Sam1224/AENet.
Paper Structure (22 sections, 2 equations, 2 figures, 1 table)

This paper contains 22 sections, 2 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Initial Submission
  3. Language
  4. Template
  5. Fonts.
  6. Paper Length
  7. Paper ID
  8. Line Numbering
  9. Policies
  10. Preserving Anonymity
  11. Formatting Guidelines
  12. Headings
  13. Figures
  14. Formulas
  15. Lemmas, Propositions, and Theorems.
  16. ...and 7 more sections

Figures (2)

  • Figure 1: One kernel at $x_s$ (dotted kernel) or two kernels at $x_i$ and $x_j$ (left and right) lead to the same summed estimate at $x_s$. This shows a figure consisting of different types of lines. Elements of the figure described in the caption should be set in italics, in parentheses, as shown in this sample caption. The last sentence of a figure caption should generally end with a full stop, except when the caption is not a full sentence.
  • Figure 2: Centered, short example caption