Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation

Download

index.pdf

Date

2023-01-01

Author

Kayabasi, Alper
Tufekci, Gulin
Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

143
views

64
downloads

Few-shot segmentation aims to devise a generalizing model that segments query images from unseen classes during training with the guidance of a few support images whose class tally with the class of the query. There exist two domain-specific problems mentioned in the previous works, namely spatial inconsistency and bias towards seen classes. Taking the former problem into account, our method compares the support feature map with the query feature map at multi scales to become scale-agnostic. As a solution to the latter problem, a supervised model, called as base learner, is trained on available classes to accurately identify pixels belonging to seen classes. Hence, subsequent meta learner has a chance to discard areas belonging to seen classes with the help of an ensemble learning model that coordinates meta learner with the base learner. We simultaneously address these two vital problems for the first time and achieve state-of-the-art performances on both PASCAL-5i and COCO-20i datasets.

Subject Keywords

Algorithms: Machine learning architectures, and algorithms (including transfer), Biomedical/healthcare/medicine, formulations, Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)

URI

https://hdl.handle.net/11511/102735

DOI

https://doi.org/10.1109/wacv56688.2023.00259

Conference Name

23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Approximate Fisher Kernels of Non-iid Image Models for Image Categorization Cinbiş, Ramazan Gökberk; Schmid, Cordelia (2016-06-01) The bag-of-words (BoW) model treats images as sets of local descriptors and represents them by visual word histograms. The Fisher vector (FV) representation extends BoW, by considering the first and second order statistics of local descriptors. In both representations local descriptors are assumed to be identically and independently distributed (iid), which is a poor assumption from a modeling perspective. It has been experimentally observed that the performance of BoW and FV representations can be improved...
Transformation of conceptual models to executable High Level Architecture federation models Özhan, Gürkan; Oğuztüzün, Mehmet Halit S. (Springer, 2015-01-01) In this chapter, we present a formal, declarative, and visual model transformation methodology to map a domain conceptual model (CM) to a distributed simulation architecture model (DSAM). The approach adheres to the principles of model-driven engineering (MDE). A two-phased automatic transformation strategy is delineated to translate a field artillery conceptual model (ACM) into a high-level architecture (HLA) federation architecture model (FAM). The produced model is then compiled by the code generator to ...
Using object-oriented materialized views to answer selection-based complex queries Alhajj, R; Polat, Faruk (1999-09-01) Presented in this paper is a model that utilizes existing materialized views to handle a wide range of complex selection-based queries, including linear recursive queries. Such queries are complex because it is almost impossible for naive users to predict the formulation of their predicate expressions. Object variables bound to objects in the result of a query are allowed to appear in the predicate of that query. Also, the predicate definition is extended to make it possible to have in the output only a sub...
Attribute-based variability in feature models Karatas, Ahmet Serkan; Oğuztüzün, Mehmet Halit S. (Springer Science and Business Media LLC, 2016-06-01) Extended feature models enable the expression of complex cross-tree constraints involving feature attributes. The inclusion of attributes in cross-tree relations not only enriches the constraints, but also engenders an extended type of variability that involves attributes. In this article, we elaborate on the effects of this new variability type on feature models. We start by analyzing the nature of the variability involving attributes and extend the definitions of the configuration and the product to suit ...
EXTRACTION OF INTERPRETABLE DECISION RULES FROM BLACK-BOX MODELS FOR CLASSIFICATION TASKS GALATALI, EGEMEN BERK; ALEMDAR, HANDE; Department of Computer Engineering (2022-8-31) In this work, we have proposed a new method and ready to use workflow to extract simplified rule sets for a given Machine Learning (ML) model trained on a classifi- cation task. Those rules are both human readable and in the form of software code pieces thanks to the syntax of Python programming language. We have inspired from the power of Shapley Values as our source of truth to select most prominent features for our rule sets. The aim of this work to select the key interval points in given data in order t...

Citation Formats

A. Kayabasi, G. Tufekci, and İ. Ulusoy, “Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation,” presented at the 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Hawaii, Amerika Birleşik Devletleri, 2023, Accessed: 00, 2023. [Online]. Available: https://hdl.handle.net/11511/102735.