Related papers: Iterative Teaching by Label Synthesis

In zero-shot learning (ZSL) community, it is generally recognized that transductive learning performs better than inductive one as the unseen-class samples are also used in its training stage. How to generate pseudo labels for unseen-class…

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…

In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets. We propose a master-teacher-student model framework to provide multi-layer guidance…

We study the problem of teaching via demonstrations in sequential decision-making tasks. In particular, we focus on the situation when the teacher has no access to the learner's model and policy, and the feedback from the learner is limited…

Learning by examples, which learns to solve a new problem by looking into how similar problems are solved, is an effective learning method in human learning. When a student learns a new topic, he/she finds out exemplar topics that are…

In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model. However, existing IMT…

Since data is the fuel that drives machine learning models, and access to labeled data is generally expensive, semi-supervised methods are constantly popular. They enable the acquisition of large datasets without the need for too many…

Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire…

The proliferation of automated data collection schemes and the advances in sensorics are increasing the amount of data we are able to monitor in real-time. However, given the high annotation costs and the time required by quality…

In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…

Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods. One efficient strategy to deal with this problem is to employ resampling techniques before…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

Modern computing and communication technologies can make data collection procedures very efficient. However, our ability to analyze large data sets and/or to extract information out from them is hard-pressed to keep up with our capacities…

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…

Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category…

Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to…

Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning, semi-supervised learning and active learning, aim to be…

In this paper, we present a learning method for sequence labeling tasks in which each example sequence has multiple label sequences. Our method learns multiple models, one model for each label sequence. Each model computes the joint…

Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is…

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…