ConceptLearner: Discovering visual concepts from weakly labeled image collections
By Bolei Zhou, Vignesh Jagadeesh, Robinson Piramuthu. 2014
48 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jiebo Luo
- Armand Joulin
- L. V. D. van der Maaten
- Allan Jabri
- Ishan Misra
- Hailin Jin
- Quoc V. Le
- Caiming Xiong
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Ming-Hsuan Yang
- Dacheng Tao
- Cordelia Schmid
- Xiaogang Wang
- Jiebo Luo
- Andrew Zisserman
Citations in the corpus
- Learning Visual Features from Large Weakly Supervised Data (2015, background): “This study is not the first to explore alternatives to training convolutional networks on manually annotated datasets [6, 10, 41, 59].”
- Learning Deep Features for Discriminative Localization (2015, neutral): “Furthermore we demonstrate that the CAM localization technique generalizes to other visual recognition tasks i.e., our technique produces generic localizable deep features that can aid other researchers in understanding the basis of discrimination used by CNNs for their tasks.”
- Image Captioning with Semantic Attention (2016, background): “It has been shown that these weakly annotated images can be exploited to learn visual concepts [38], text-image embedding [14] and image captions [7].”
- Deep learning for visual understanding (2017, unknown): “Two other promising, scalable approaches are ConceptLeaner [168] and BabyLearning [169].”