• Home
  • Search
  • Object Recognition via Local Patch Labelling
  • Cite Icon16
  • https://doi.org/10.1007/11559887_1Copy DOI Icon

Object Recognition via Local Patch Labelling

  • Jan 1, 2005
  • Christopher M Bishop +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of this problem is to be able to recognize any member of a category of objects in spite of wide variations in visual appearance due to variations in the form and colour of the object, occlusions, geometrical transformations (such as scaling and rotation), changes in illumination, and potentially non-rigid deformations of the object itself. In this paper we focus on the detection of objects within images by combining information from a large number of small regions, or ‘patches’, of the image. Since detailed hand-segmentation and labelling of images is very labour intensive, we make use of ‘weakly labelled’ data in which the training images are labelled only according to the presence or absence of each category of object. A major challenge presented by this problem is that the foreground object is accompanied by widely varying background clutter, and the system must learn to distinguish the foreground from the background without the aid of labelled data. In this paper we first show that patches which are highly relevant for the object discrimination problem can be selected automatically from a large dictionary of candidate patches during learning, and that this leads to improved classification compared to direct use of the full dictionary. We then explore alternative techniques which are able to provide labels for the individual patches, as well as for the image as a whole, so that each patch is identified as belonging to one of the object categories or to the background class. This provides a rough indication of the location of the object or objects within the image. Again these individual patch labels must be learned on the basis only of overall image class labels. We develop two such approaches, one discriminative and one generative, and compare their performance both in terms of patch labelling and image labelling. Our results show that good classification performance can be obtained on challenging data sets using only weak training labels, and they also highlight some of the relative merits of discriminative and generative approaches.

Similar Papers
  • Research Article
  • Citations13

Subclass linear discriminant analysis for video-based face recognition

  • Aug 21, 2009
  • Journal of Visual Communication and Image Representation
  • Aristodemos Pnevmatikakis +1
  • Research Article
  • Citations34

Learning Object Detectors With Semi-Annotated Weak Labels

  • Dec 01, 2019
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Dingwen Zhang +3
  • Conference Article
  • Citations26

Salvage of Supervision in Weakly Supervised Object Detection

  • Jun 01, 2022
  • Lin Sui +2
  • Research Article
  • Citations34

Weak-Labeled Active Learning With Conditional Label Dependence for Multilabel Image Classification

  • Jun 01, 2017
  • IEEE Transactions on Multimedia
  • Jian Wu +6
  • Research Article
  • Citations11

Deep labeller: automatic bounding box generation for synthetic violence detection datasets

  • Jun 24, 2023
  • Multimedia Tools and Applications
  • Muhammad Shahroz Nadeem +4
  • Conference Article
  • Citations2

A comparative analysis of face annotation schemes for web facial images in social networks

  • Mar 01, 2015
  • C Nandhagopal +1
  • Conference Article
  • Citations10

Weak Labeled Multi-Label Active Learning for Image Classification

  • Oct 13, 2015
  • Shiquan Zhao +5
  • Research Article

Weakly Supervised Salient Object Detection Based on Image Semantics

  • Feb 01, 2021
  • Journal of Computer-Aided Design & Computer Graphics
  • Shimin Zhao +4
  • Research Article
  • Citations10

Visual positioning of previously defined ROIs on microscopic slides

  • Jan 01, 2006
  • IEEE Transactions on Information Technology in Biomedicine
  • G Begelman +2
  • Conference Article
  • Citations5

Map-Based Microscope Positioning

  • Jan 01, 2004
  • G Begelman +2
  • Conference Article
  • Citations37

Repeated Pattern Detection Using CNN Activations

  • Mar 01, 2017
  • Louis Lettry +3
  • Research Article
  • Citations1

A discriminative graph inferring framework towards weakly supervised image parsing

  • Mar 24, 2015
  • Multimedia Systems
  • Lei Yu +2
  • Conference Article
  • Citations6

Autonomous Object Detection in Satellite Images Using Wfrcnn

  • Dec 01, 2020
  • Nour Aburaed +5
  • Research Article
  • Citations40

Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images.

  • Oct 01, 2015
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Zhiyuan Shi +2
  • Conference Article
  • Citations4

Video-based object recognition with weakly supervised object localization

  • Nov 01, 2015
  • Yang Liu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.