Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 27, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Weakly Supervised Large Scale Object Localization with Multiple Instance Learning and Bag Splitting.

Weiqiang Ren, Kaiqi Huang, Dacheng Tao

IEEE Transactions on Pattern Analysis and Machine Intelligence

|January 14, 2016

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Holistic Invariant Retracing for Distortion-Resilient Multi-Modal Learning in Spatial Transcriptomics.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Demonstration of efficient predictive surrogates for large-scale quantum processors.

Nature communications·2026

Same author

A DeepSeek-powered AI system for automated chest radiograph interpretation in clinical practice.

Nature communications·2026

Same author

NoisePO: Efficient Semantic Noise Generation and Ranking for Diffusion-Based Text-to-Image Synthesis.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Stability and Generalization for Distributed SGDA.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

We developed MILinear, a novel framework for object localization using only image-level labels. This approach efficiently learns from large datasets without bounding box annotations, outperforming existing methods.

Area of Science:

Computer Vision
Machine Learning

Background:

Object localization from image-level labels is difficult, especially with cluttered backgrounds and large datasets.
Existing methods often require specific features and struggle with scalability.

Purpose of the Study:

To propose an efficient and effective learning framework, MILinear, for object localization.
To enable learning from large-scale data without bounding box annotations.
To improve scalability for real-world applications.

Main Methods:

Integrated prior knowledge using a large pre-trained convolutional network.
Developed a bag-splitting algorithm to reduce ambiguity in positive images by generating negative bags.
Trained and evaluated the MILinear framework on challenging datasets like Pascal VOC 2007 and ILSVRC 2013.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Related Experiment Videos

Last Updated: Mar 27, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Main Results:

MILinear significantly outperformed state-of-the-art methods on the Pascal VOC 2007 dataset.
Achieved results comparable to fully supervised models despite lacking bounding box annotations.
Demonstrated superior performance on the ILSVRC 2013 detection dataset compared to supervised models without box annotations.

Conclusions:

MILinear offers an efficient and effective solution for object localization using only image-level labels.
The framework demonstrates strong scalability and performance, even surpassing some supervised methods.
This approach advances visual recognition tasks by reducing the need for precise annotations.