Abstract
Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object bounding boxes, however, is both expensive and often subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects. We quantify its object classification and object location prediction performance on the Pascal VOC 2012 (20 object classes) and the much larger Microsoft COCO (80 object classes) datasets. We find that the network (i) outputs accurate image-level labels, (ii) predicts approximate locations (but not extents) of objects, and (iii) performs comparably to its fully-supervised counterparts using object bounding box annotation for training.
Keywords
Pascal (unit)Artificial intelligenceConvolutional neural networkComputer scienceBounding overwatchMinimum bounding boxObject (grammar)AnnotationPattern recognition (psychology)Cognitive neuroscience of visual object recognitionObject detectionSupervised learningContextual image classificationArtificial neural networkComputer visionImage (mathematics)Machine learning
Affiliated Institutions
Related Publications
Learning Deep Features for Discriminative Localization
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable...
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...
ConceptLearner: Discovering visual concepts from weakly labeled image collections
Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition systems, since it is expensive to obtain fully labeled data for a large ...
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that...
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large- scale visual recognition challenge (ILSVRC2012). The success o...
Publication Info
- Year
- 2015
- Type
- preprint
- Citations
- 915
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
915
OpenAlex
Cite This
Maxime Oquab,
Léon Bottou,
Ivan Laptev
et al.
(2015).
Is object localization for free? - Weakly-supervised learning with convolutional neural networks.
.
https://doi.org/10.1109/cvpr.2015.7298668
Identifiers
- DOI
- 10.1109/cvpr.2015.7298668