Multi-fold MIL Training for Weakly Supervised Object Localization

2014-06-01 · CVPR 2014 6 · Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid

Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when high-dimensional representations, such as the Fisher vectors, are used. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset. Compared to state-of-the-art weakly supervised detectors, our approach better localizes objects in the training images, which translates into improved detection performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance LearningObjectObject LocalizationWeakly-supervised LearningWeakly-Supervised Object Localization

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

2015-03-03 · Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid

Multiple Instance Learning Object Object Localization Weakly-supervised Learning+1

Solving weakly supervised regression problem using low-rank manifold regularization

2021-04-13 · Vladimir Berikov, Alexander Litvinenko

We solve a weakly supervised regression problem. Under "weakly" we understand that for some training points the labels are known, for some unknown, and for others uncertain due to the presence of random noise or other re…

Clustering regression

Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning

2018-02-26 · CVPR 2018 6 · Weifeng Ge, Sibei Yang, Yizhou Yu

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predi…

Clustering General Classification image-classification Image Classification+15

CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns

2020-11-02 · Ruining Deng, Quan Liu, Shunxing Bao, Aadarsh Jha 외

Weakly supervised learning has been rapidly advanced in biomedical image analysis to achieve pixel-wise labels (segmentation) from image-wise annotations (classification), as biomedical images naturally contain image-wis…

Image Reconstruction Segmentation Weakly-supervised Learning Weakly supervised segmentation

One-Shot Weakly Supervised Video Object Segmentation

2019-12-18 · Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao 외

Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks. Recent work has shown to perform on par with weaker levels of supe…

Object Segmentation Semantic Segmentation Video Object Segmentation+2