Beyond invariance: test-time label-shift adaptation for addressing "spurious" correlations
Abstract
Supplementary Material
- Download
- 507.26 KB
References
Recommendations
Unsupervised adversarial invariance
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsData representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing ...
One-Bit Supervision for Image Classification: Problem, Solution, and Beyond
This article presents one-bit supervision, a novel setting of learning with fewer labels, for image classification. Instead of the training model using the accurate label of each sample, our setting requires the model to interact with the system by ...
Beyond Object Proposals: Random Crop Pooling for Multi-Label Image Recognition
Learning high-level image representations using object proposals has achieved remarkable success in multi-label image recognition. However, most object proposals provide merely coarse information about the objects, and only carefully selected proposals ...
Comments
Information & Contributors
Information
Published In
Publisher
Curran Associates Inc.
Red Hook, NY, United States
Publication History
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0