• Title/Summary/Keyword: WSOL

Search Result 3, Processing Time 0.015 seconds

Expanded Object Localization Learning Data Generation Using CAM and Selective Search and Its Retraining to Improve WSOL Performance (CAM과 Selective Search를 이용한 확장된 객체 지역화 학습데이터 생성 및 이의 재학습을 통한 WSOL 성능 개선)

  • Go, Sooyeon;Choi, Yeongwoo
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.10 no.9
    • /
    • pp.349-358
    • /
    • 2021
  • Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.

Integration of Multi-scale CAM and Attention for Weakly Supervised Defects Localization on Surface Defective Apple

  • Nguyen Bui Ngoc Han;Ju Hwan Lee;Jin Young Kim
    • Smart Media Journal
    • /
    • v.12 no.9
    • /
    • pp.45-59
    • /
    • 2023
  • Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

An Ubiquitous Web Service Architecture for IP-based Ubiquitous Service (IP 기반의 유비쿼터스 서비스를 위한 유비쿼터스 웹 서비스 아키텍처)

  • Choi, Jae-Hyun;Lee, Woo-Jin;Chong, Ki-Won
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2005.11b
    • /
    • pp.481-483
    • /
    • 2005
  • IT 기술의 눈부신 성장과 함께 가시화되고 있는 유비쿼터스 환경은 언제 어디서나 사용자가 원하는 서비스를 제공 받을 수 있는 환경으로, 무선통신기술 및 개체 식별 기술 등의 발달과 더불어 점점 현실화되고 있다. 하지만, 모든 유비쿼터스 개체에 IP가 부여되고 이를 기반으로 하는 진정한 유비쿼터스 환경이 현실화되기에는 아직까지 IPv6등 실질적인 인프라가 완벽하게 구축되어 있지 않아 다소 어려운 점이 있다. 따라서, 본 논문에서는 IPv4 환경에서 웹 서비스를 이용하여 실질적인 IP기반의 유비쿼터스 환경을 실현하기 위한 아키텍처를 제시한다. 이 아키텍처는 IPv4 및 IPv6에서 동작 가능하며, PC 및 핸드폰, PDA, 홈 가전기기 등의 모든 기기들을 연결한 통합 네트워크 환경상에서 실질적인 유비쿼터스 서비스의 실현을 목적으로 한다. 이러한 유비쿼터스 웹 서비스 아키텍처상에서, 유비쿼터스 서비스를 제공하는 개체는 유비쿼터스 웹 서비스 명세언어인 uWSOL을 통해 명세되고, 해당 유비쿼터스 서비스를 사용하고자 하는 사용자가 이를 바탕으로 해당 개체와 적절한 메시지 통신을 주고 받을 수 있게 함으로써 유비쿼터스 환경을 실현한다.

  • PDF