A Testbed for Cross-Dataset Analysis
arXiv:1402.5923
Abstract
Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections. The number of available datasets is still progressively growing together with the amount of samples per object category. However, this trend does not correspond directly to an increasing in the generalization capabilities of the developed recognition systems. Each collection tends to have its specific characteristics and to cover just some aspects of the visual world: these biases often narrow the effect of the methods defined and tested separately over each image set. Our work makes a first step towards the analysis of the dataset bias problem on a large scale. We organize twelve existing databases in a unique corpus and we present the visual community with a useful feature repository for future research.
References in corpus (1)
Cited by in corpus (15)
- VisDA: The Visual Domain Adaptation Challenge
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- A Benchmark and Comparison of Active Learning for Logistic Regression
- Learning Factorized Representations for Open-set Domain Adaptation
- Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
- Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
- A Deeper Look at Dataset Bias
- Deep Domain Adaptation by Geodesic Distance Minimization
- Towards an Understanding of Neural Networks in Natural-Image Spaces
- Cross-Dataset Adaptation for Visual Question Answering
- Accelerated kernel discriminant analysis
- Are You Tampering With My Data?
- Open Set Domain Adaptation for Image and Action Recognition
- Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets
- Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval