Corpus ID: 237156316

Efficient Algorithms for Learning from Coarse Labels

  title={Efficient Algorithms for Learning from Coarse Labels},
  author={Dimitris Fotakis and Alkis Kalavasis and Vasilis Kontonis and Christos Tzamos},
For many learning problems one may not have access to fine grained label information; e.g., an image can be labeled as husky, dog, or even animal depending on the expertise of the annotator. In this work, we formalize these settings and study the problem of learning from such coarse data. Instead of observing the actual labels from a set Z , we observe coarse labels corresponding to a partition of Z (or a mixture of partitions). Our main algorithmic result is that essentially any problem… Expand

Figures from this paper

Label Ranking through Nonparametric Regression
A generative model for Label Ranking is introduced, in noiseless and noisy nonparametric regression settings, and sample complexity bounds for learning algorithms in both cases are provided. Expand
Coarse-To-Fine Incremental Few-Shot Learning
  • Xiang Xiang, Yuwen Tan, Qian Wan, Jing Ma
  • Computer Science
  • ArXiv
  • 2021
Knowe is proposed: to learn, normalize, and freeze a classifier’s weights from fine labels, once learning an embedding space contrastively from coarse labels, which outperforms all recent relevant CIL/FSCIL methods that are tailored to the new problem setting for the first time. Expand


Weakly Supervised Image Classification with Coarse and Fine Labels
A model based on convolutional neural networks (CNNs) is proposed to address image classification in a weakly supervised scenario where the training data are annotated at different levels of abstractions and significantly outperforms the naive approach that discards the extra coarsely labeled data. Expand
Grafit: Learning fine-grained image representations with coarse labels
This paper tackles the problem of learning a finer representation than the one provided by training labels, which enables fine-grained category retrieval of images in a collection annotated with coarse labels only and significantly improves the accuracy of category-level retrieval methods. Expand
Weakly labeled fine-grained classification with hierarchy relationship of fine and coarse labels
This paper proposes to make fine labels prediction under a weakly supervised setting where a subset of training data is labeled with fine labels and the others only have coarse labels, and aims to explore the hierarchy relationship between coarse classes and fine classes to achieve a better performance on fine-grained classification. Expand
A Weakly Supervised Fine Label Classifier Enhanced by Coarse Supervision
This paper addresses the challenge of fine image classification in a weakly supervised fashion, whereby a subset of images is tagged by fine labels, while the remaining are tagged by coarse labels with a new deep model that leverages coarse images to improve the classification performance of fine images within the coarse category. Expand
Understanding the Impact of Label Granularity on CNN-Based Image Classification
The experimental results show that training CNNs with fine-grain labels improves both network's optimization and generalization capabilities, as intuitively it encourages the network to learn more features, and hence increases classification accuracy on coarse-grain classes under all datasets considered. Expand
Fine-Grained Image Classification with Coarse and Fine Labels on One-Shot Learning
This paper introduces the hierarchical structure between coarse and fine labels to exploit the relationship among categories and fuse the results of relation network and those of fine label prediction to produce more robust and more accurate classification results. Expand
From categories to subcategories: Large-scale image classification with partial class label refinement
This work investigates how coarse category labels can be used to improve the classification of subcategories and adopts the framework of Random Forests and proposes a regularized objective function that takes into account relations between categories and subc categories. Expand
Efficient noise-tolerant learning from statistical queries
This paper formalizes a new but related model of learning from statistical queries, and demonstrates the generality of the statistical query model, showing that practically every class learnable in Valiant’s model and its variants can also be learned in the new model (and thus can be learning in the presence of noise). Expand
Statistical Query Lower Bounds for Robust Estimation of High-Dimensional Gaussians and Gaussian Mixtures
A general technique that yields the first Statistical Query lower bounds for a range of fundamental high-dimensional learning problems involving Gaussian distributions is described, which implies that the computational complexity of learning GMMs is inherently exponential in the dimension of the latent space even though there is no such information-theoretic barrier. Expand
Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration
This work utilizes imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation of physiological states. Expand