DeepAI AI Chat
Log In Sign Up

Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images

by   Stefan Mathe, et al.

State-of-the-art visual recognition and detection systems increasingly rely on large amounts of training data and complex classifiers. Therefore it becomes increasingly expensive both to manually annotate datasets and to keep running times at levels acceptable for practical applications. In this paper, we propose two solutions to address these issues. First, we introduce a weakly supervised, segmentation-based approach to learn accurate detectors and image classifiers from weak supervisory signals that provide only approximate constraints on target localization. We illustrate our system on the problem of action detection in static images (Pascal VOC Actions 2012), using human visual search patterns as our training signal. Second, inspired from the saccade-and-fixate operating principle of the human visual system, we use reinforcement learning techniques to train efficient search models for detection. Our sequential method is weakly supervised and general (it does not require eye movements), finds optimal search strategies for any given detection confidence function and achieves performance similar to exhaustive sliding window search at a fraction of its computational cost.


page 2

page 8


Defect detection using weakly supervised learning

In many real-world scenarios, obtaining large amounts of labeled data ca...

Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection

Modern deep learning models require large amounts of accurately annotate...

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

Weakly supervised temporal action detection is a Herculean task in under...

Self Paced Deep Learning for Weakly Supervised Object Detection

In a weakly-supervised scenario object detectors need to be trained usin...

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

The challenging field of scene text detection requires complex data anno...

A deep Q-learning method for optimizing visual search strategies in backgrounds of dynamic noise

Humans process visual information with varying resolution (foveated visu...

Weakly Supervised Universal Fracture Detection in Pelvic X-rays

Hip and pelvic fractures are serious injuries with life-threatening comp...