Abstract
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 number of concept categories. In this paper, we propose ConceptLearner, which is a scalable approach to discover visual concepts from weakly labeled image collections. Thousands of visual concept detectors are learned automatically, without human in the loop for additional annotation. We show that these learned detectors could be applied to recognize concepts at image-level and to detect concepts at image region-level accurately. Under domain-specific supervision, we further evaluate the learned concepts for scene recognition on SUN database and for object detection on Pascal VOC 2007. ConceptLearner shows promising performance compared to fully supervised and weakly supervised methods.
Keywords
Pascal (unit)Computer scienceArtificial intelligenceAnnotationScalabilityObject detectionLabeled dataPattern recognition (psychology)Image (mathematics)Domain (mathematical analysis)Cognitive neuroscience of visual object recognitionDetectorVisualizationAutomatic image annotationContextual image classificationComputer visionObject (grammar)Image retrievalDatabase
Affiliated Institutions
Related Publications
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object boundi...
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...
Momentum Contrast for Unsupervised Visual Representation Learning
We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic diction...
FCOS: Fully Convolutional One-Stage Object Detection
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether...
Publication Info
- Year
- 2015
- Type
- preprint
- Pages
- 1492-1500
- Citations
- 40
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
40
OpenAlex
Cite This
Bolei Zhou,
Vignesh Jagadeesh,
Robinson Piramuthu
(2015).
ConceptLearner: Discovering visual concepts from weakly labeled image collections.
, 1492-1500.
https://doi.org/10.1109/cvpr.2015.7298756
Identifiers
- DOI
- 10.1109/cvpr.2015.7298756