Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
International Journal of Computer Vision
Optimizing search engines using clickthrough data
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Multimedia semantic indexing using model vectors
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 1
Large-Scale Concept Ontology for Multimedia
IEEE MultiMedia
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
CuZero: embracing the frontier of interactive visual search for informed users
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Active learning by labeling features
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic attribute discovery and characterization from noisy web data
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Semantic label sharing for learning with many categories
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Visual recognition with humans in the loop
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
A discriminative latent model of object classes and attributes
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Interactively building a discriminative vocabulary of nameable attributes
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Combining attributes and Fisher vectors for efficient image retrieval
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Bridging the Gap: Query by Semantic Example
IEEE Transactions on Multimedia
Annotator rationales for visual recognition
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Actively selecting annotations among objects and attributes
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Multiclass recognition and part localization with humans in the loop
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Describing people: A poselet-based approach to attribute classification
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
A joint learning framework for attribute models and object descriptions
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Constrained semi-supervised learning using attributes and comparative attributes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Constrained semi-supervised learning using attributes and comparative attributes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
Traditional active learning allows a (machine) learner to query the (human) teacher for labels on examples it finds confusing. The teacher then provides a label for only that instance. This is quite restrictive. In this paper, we propose a learning paradigm in which the learner communicates its belief (i.e. predicted label) about the actively chosen example to the teacher. The teacher then confirms or rejects the predicted label. More importantly, if rejected, the teacher communicates an explanation for why the learner's belief was wrong. This explanation allows the learner to propagate the feedback provided by the teacher to many unlabeled images. This allows a classifier to better learn from its mistakes, leading to accelerated discriminative learning of visual concepts even with few labeled images. In order for such communication to be feasible, it is crucial to have a language that both the human supervisor and the machine learner understand. Attributes provide precisely this channel. They are human-interpretable mid-level visual concepts shareable across categories e.g. "furry", "spacious", etc. We advocate the use of attributes for a supervisor to provide feedback to a classifier and directly communicate his knowledge of the world. We employ a straightforward approach to incorporate this feedback in the classifier, and demonstrate its power on a variety of visual recognition scenarios such as image classification and annotation. This application of attributes for providing classifiers feedback is very powerful, and has not been explored in the community. It introduces a new mode of supervision, and opens up several avenues for future research.