Curriculum Learning with Diversity for Supervised Computer Vision Tasks
- URL: http://arxiv.org/abs/2009.10625v1
- Date: Tue, 22 Sep 2020 15:32:49 GMT
- Title: Curriculum Learning with Diversity for Supervised Computer Vision Tasks
- Authors: Petru Soviany
- Abstract summary: We introduce a novel curriculum sampling strategy which takes into consideration the diversity of the training data together with the difficulty of the inputs.
We prove that our strategy is very efficient for unbalanced data sets, leading to faster convergence and more accurate results.
- Score: 1.5229257192293197
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Curriculum learning techniques are a viable solution for improving the
accuracy of automatic models, by replacing the traditional random training with
an easy-to-hard strategy. However, the standard curriculum methodology does not
automatically provide improved results, but it is constrained by multiple
elements like the data distribution or the proposed model. In this paper, we
introduce a novel curriculum sampling strategy which takes into consideration
the diversity of the training data together with the difficulty of the inputs.
We determine the difficulty using a state-of-the-art estimator based on the
human time required for solving a visual search task. We consider this kind of
difficulty metric to be better suited for solving general problems, as it is
not based on certain task-dependent elements, but more on the context of each
image. We ensure the diversity during training, giving higher priority to
elements from less visited classes. We conduct object detection and instance
segmentation experiments on Pascal VOC 2007 and Cityscapes data sets,
surpassing both the randomly-trained baseline and the standard curriculum
approach. We prove that our strategy is very efficient for unbalanced data
sets, leading to faster convergence and more accurate results, when other
curriculum-based strategies fail.
Related papers
- Data-CUBE: Data Curriculum for Instruction-based Sentence Representation
Learning [85.66907881270785]
We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training.
In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk.
In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
arXiv Detail & Related papers (2024-01-07T18:12:20Z) - NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision
Research [96.53307645791179]
We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks.
Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth.
Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
arXiv Detail & Related papers (2022-11-15T18:57:46Z) - Improving Imbalanced Text Classification with Dynamic Curriculum
Learning [32.731900584216724]
We propose a novel self-paced dynamic curriculum learning method for imbalanced text classification.
Our SPDCL can reorder and resample training data by difficulty criterion with an adaptive from easy to hard pace.
The experiments on several classification tasks show the effectiveness of SPDCL strategy, especially for the imbalanced dataset.
arXiv Detail & Related papers (2022-10-25T07:57:59Z) - Let the Model Decide its Curriculum for Multitask Learning [22.043291547405545]
We propose two classes of techniques to arrange training instances into a learning curriculum based on difficulty scores computed via model-based approaches.
We show that instance-level and dataset-level techniques result in strong representations as they lead to an average performance improvement of 4.17% and 3.15% over their respective baselines.
arXiv Detail & Related papers (2022-05-19T23:34:22Z) - Budget-aware Few-shot Learning via Graph Convolutional Network [56.41899553037247]
This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples.
A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels.
We introduce a new budget-aware few-shot learning problem that aims to learn novel object categories.
arXiv Detail & Related papers (2022-01-07T02:46:35Z) - Curriculum Meta-Learning for Few-shot Classification [1.5039745292757671]
We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification.
Our experiments with the MAML algorithm on two few-shot image classification tasks show significant gains with the curriculum training framework.
arXiv Detail & Related papers (2021-12-06T10:29:23Z) - Statistical Measures For Defining Curriculum Scoring Function [5.328970912536596]
We show improvements in performance with convolutional and fully-connected neural networks on real image datasets.
Motivated by our insights from implicit curriculum ordering, we introduce a simple curriculum learning strategy.
We also propose and study the performance of a dynamic curriculum learning algorithm.
arXiv Detail & Related papers (2021-02-27T07:25:49Z) - Improving filling level classification with adversarial training [90.01594595780928]
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass.
We use adversarial training in a generic source dataset and then refine the training with a task-specific dataset.
We show that transfer learning with adversarial training in the source domain consistently improves the classification accuracy on the test set.
arXiv Detail & Related papers (2021-02-08T08:32:56Z) - Curriculum Learning: A Survey [65.31516318260759]
Curriculum learning strategies have been successfully employed in all areas of machine learning.
We construct a taxonomy of curriculum learning approaches by hand, considering various classification criteria.
We build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm.
arXiv Detail & Related papers (2021-01-25T20:08:32Z) - Adaptive Task Sampling for Meta-Learning [79.61146834134459]
Key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time.
We propose an adaptive task sampling method to improve the generalization performance.
arXiv Detail & Related papers (2020-07-17T03:15:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.