On Deep Unsupervised Active Learning
- URL: http://arxiv.org/abs/2007.13959v1
- Date: Tue, 28 Jul 2020 02:52:21 GMT
- Title: On Deep Unsupervised Active Learning
- Authors: Changsheng Li and Handong Ma and Zhao Kang and Ye Yuan and Xiao-Yu
Zhang and Guoren Wang
- Abstract summary: Unsupervised active learning aims to select representative samples in an unsupervised setting for human annotating.
In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning.
- Score: 41.579343330613675
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Unsupervised active learning has attracted increasing attention in recent
years, where its goal is to select representative samples in an unsupervised
setting for human annotating. Most existing works are based on shallow linear
models by assuming that each sample can be well approximated by the span (i.e.,
the set of all linear combinations) of certain selected samples, and then take
these selected samples as representative ones to label. However, in practice,
the data do not necessarily conform to linear models, and how to model
nonlinearity of data often becomes the key point to success. In this paper, we
present a novel Deep neural network framework for Unsupervised Active Learning,
called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input
into a latent space through an encoder-decoder architecture, and introduce a
selection block to select representative samples in the the learnt latent
space. In the selection block, DUAL considers to simultaneously preserve the
whole input patterns as well as the cluster structure of data. Extensive
experiments are performed on six publicly available datasets, and experimental
results clearly demonstrate the efficacy of our method, compared with
state-of-the-arts.
Related papers
- Diversified Batch Selection for Training Acceleration [68.67164304377732]
A prevalent research line, known as online batch selection, explores selecting informative subsets during the training process.
vanilla reference-model-free methods involve independently scoring and selecting data in a sample-wise manner.
We propose Diversified Batch Selection (DivBS), which is reference-model-free and can efficiently select diverse and representative samples.
arXiv Detail & Related papers (2024-06-07T12:12:20Z) - Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels.
Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
arXiv Detail & Related papers (2024-04-26T06:00:27Z) - Towards Free Data Selection with General-Purpose Models [71.92151210413374]
A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets.
Current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly.
FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods.
arXiv Detail & Related papers (2023-09-29T15:50:14Z) - Exploring Data Redundancy in Real-world Image Classification through
Data Selection [20.389636181891515]
Deep learning models often require large amounts of data for training, leading to increased costs.
We present two data valuation metrics based on Synaptic Intelligence and gradient norms, respectively, to study redundancy in real-world image data.
Online and offline data selection algorithms are then proposed via clustering and grouping based on the examined data values.
arXiv Detail & Related papers (2023-06-25T03:31:05Z) - Towards General and Efficient Active Learning [20.888364610175987]
Active learning aims to select the most informative samples to exploit limited annotation budgets.
We propose a novel general and efficient active learning (GEAL) method in this paper.
Our method can conduct data selection processes on different datasets with a single-pass inference of the same model.
arXiv Detail & Related papers (2021-12-15T08:35:28Z) - Active Learning for Deep Visual Tracking [51.5063680734122]
Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years.
In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model.
Under the guidance of active learning, the tracker based on the trained deep CNNs model can achieve competitive tracking performance while reducing the labeling cost.
arXiv Detail & Related papers (2021-10-17T11:47:56Z) - Message Passing Adaptive Resonance Theory for Online Active
Semi-supervised Learning [30.19936050747407]
We propose Message Passing Adaptive Resonance Theory (MPART) for online active semi-supervised learning.
MPART infers the class of unlabeled data and selects informative and representative samples through message passing between nodes on the topological graph.
We evaluate our model with comparable query selection strategies and frequencies, showing that MPART significantly outperforms the competitive models in online active learning environments.
arXiv Detail & Related papers (2020-12-02T14:14:42Z) - Online Active Model Selection for Pre-trained Classifiers [72.84853880948894]
We design an online selective sampling approach that actively selects informative examples to label and outputs the best model with high probability at any round.
Our algorithm can be used for online prediction tasks for both adversarial and streams.
arXiv Detail & Related papers (2020-10-19T19:53:15Z) - Deep Active Learning by Model Interpretability [7.3461534048332275]
In this paper, we introduce the linearly separable regions of samples to the problem of active learning.
We propose a novel Deep Active learning approach by Model Interpretability (DAMI)
To keep the maximal representativeness of the entire unlabeled data, DAMI tries to select and label samples on different linearly separable regions.
arXiv Detail & Related papers (2020-07-23T16:06:27Z)
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.