Improving Generalization via Scalable Neighborhood Component Analysis
arXiv:1808.04699
Abstract
Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training. However, this becomes problematic for open-set scenarios where new categories are encountered with very few examples for learning a generalizable parametric classifier. We adopt a non-parametric approach for visual recognition by optimizing feature embeddings instead of parametric classifiers. We use a deep neural network to learn the visual feature that preserves the neighborhood structure in the semantic space, based on the Neighborhood Component Analysis (NCA) criterion. Limited by its computational bottlenecks, we devise a mechanism to use augmented memory to scale NCA for large datasets and very deep networks. Our experiments deliver not only remarkable performance on ImageNet classification for such a simple non-parametric method, but most importantly a more generalizable feature representation for sub-category discovery and few-shot recognition.
To appear in ECCV 2018
References in corpus (7)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- A Simple Neural Attentive Meta-Learner
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- What makes ImageNet good for transfer learning?
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- Sampling Matters in Deep Embedding Learning
Cited by in corpus (5)
- Classification is a Strong Baseline for Deep Metric Learning
- Temperature check: theory and practice for training models with softmax-cross-entropy losses
- Deep Metric Transfer for Label Propagation with Limited Annotated Data
- Spectral Feature Transformation for Person Re-identification
- Calibrated neighborhood aware confidence measure for deep metric learning