Learning Loss for Active Learning

Yoo, Donggeun; Kweon, In So

doi:10.1109/cvpr.2019.00018

Cited by 504 publications

(569 citation statements)

References 48 publications

Supporting

Mentioning

520

Contrasting

Order By: Relevance

“…If a loss is given to the model, the given loss would force it to increasel i and decreasel j . In this way, the loss prediction model completely discard the overall scale changes [41]. To this end, the final loss function is computed as:…”

Section: B Active Deep Densely Connected Convolutional Networkmentioning

confidence: 99%

Semisupervised graph convolutional network for hyperspectral image classification

Liu

Gao

et al. 2020

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very challenging to use only a few labeled samples to train deep learning models to reach a high classification accuracy. An active deep-learning framework trained by an end-to-end manner is, therefore, proposed by this paper in order to minimize the hyperspectral image classification costs. First, a deep densely connected convolutional network is considered for hyperspectral image classification. Different from the traditional active learning methods, an additional network is added to the designed deep densely connected convolutional network to predict the loss of input samples. Then, the additional network could be used to suggest unlabeled samples that the deep densely connected convolutional network is more likely to produce a wrong label. Note that the additional network uses the intermediate features of the deep densely connected convolutional network as input. Therefore, the proposed method is an end-to-end framework. Subsequently, a few of the selected samples are labelled manually and added to the training samples. The deep densely connected convolutional network is therefore trained using the new training set. Finally, the steps above are repeated to train the whole framework iteratively. Extensive experiments illustrates that the method proposed could reach a high accuracy in classification after selecting just a few samples.

show abstract

Section: B Active Deep Densely Connected Convolutional Networkmentioning

confidence: 99%

Semisupervised graph convolutional network for hyperspectral image classification

Liu

Gao

et al. 2020

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…The problem is that manual annotation of sentiment labels takes time and manpower. Meanwhile, the budget for annotation is limited [5]. Most of the existing emotion datasets that are no more than 1,000 images [2].…”

Section: B Active Learningmentioning

confidence: 99%

“…The LP module is attached to the traditional CNN, which uses the representation of multi-level layer of the traditional CNN. After each of the active learning cycle, all the affective samples are evaluated in the unlabeled pool by the LP module to obtain data-loss pairs {(x i , Ll i )|x i ∈ U }, then human oracles manually annotate the samples of the Khighest losses [5]:…”

Section: B Uncertainty Sampling For Affective Samples Selectionmentioning

confidence: 99%

“…It can get better classification accuracy when using more annotated samples. However, the labeled samples are not available and enough for annotation labor and cost of time [5], which is a challenge in the VSA. In addition, image labeling is more difficult than traditional vision tasks for that the emotions are not absolutely independent in the aspect of semantic.…”

Section: Introductionmentioning

confidence: 99%

“…Given an unlabeled data pool, active learner evaluates all instances in this pool and selectively queries useful samples from the pool. There have been three major selection criteria: uncertainty sampling approach, diversitybased approach and expected model change [5]. The simplest and most commonly used query framework is uncertainty sampling.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual Sentiment Analysis With Active Learning

2020

View full text Add to dashboard Cite

Visual Sentiment Analysis (VSA) has attracted wide attention since more and more people are willing to express their emotion and opinions via visual contents on social media. Meanwhile, extensive datasets drive the rapid development of deep neural networks for this task. However, the annotation of large-scale datasets is very expensive and time consuming. In this paper, we propose a novel active learning framework, which uses few labeled training samples to achieve an effective sentiment analysis model. First, we attach a new branch to the traditional Convolution Neural Network (CNN), which is named "texture module". The affective vector will be obtained by computing inner products of feature maps from different convolutional blocks in this branch. We will utilize this vector to distinguish affective images. Second, the query strategy is formed by the classification scores from both the traditional CNN and the texture module. Then, we can use samples obtained by utilizing the query strategy to train our model. Extensive experiments on four public affective datasets show that our approach uses few labeled training samples to achieve promising results for VSA.

show abstract

Artificial intelligence of things (AIoT) data acquisition based on graph neural networks: A systematical review

Wang

Zhang

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe power of artificial intelligence of things (AIoT) stems from adapting machine learning (ML) and artificial intelligence (AI) models into abundant intelligent IoT fields, based on a large data stream with different formats, sizes, and timestamps generated by massive numbers of heterogeneous sensors. On the one hand, data acquisition is the fundamental basis for any AIoT systems, but data sensed by massive IoT devices may be noisy and even contain adversarial samples. On the other hand, ensuring the efficiency and robustness in data acquisition is vitally important for data‐driven ML and AI. Recently, besides perceiving ability, the literature has witnessed great development of empowering things with learning and reasoning ability through deep learning models, including recurrent neural networks (RNNs) and/or convolutional neural network (CNNs). However, the existing works have one significant weakness: fail to explicitly leverage the geospatial implications and latent connections among sensors for high‐quality data acquisition and quality control. Graphs are intrinsically suitable for representing the dependencies and inter‐relationships between AIoT data sensing devices. Due to the ability of capturing the complex interactive relationships between nodes and producing high‐level representations of the graph input, graph neural networks (GNNs) have exploded onto various ML and AI fields, to learn from graph‐structured data. Our review covers the latest progresses in GNN for the fundamental atomic task of data acquisition in AIoT. Instead of surveying the abundant GNN schemes in vertically various IoT sensing applications, this paper systematically reviews the horizontal infrastructure that all AIoT fields should have, that is, AIoT data acquisition, based on GNN and other related emerging AI factors. Our contributions include the following aspects: Provide the latest progresses in GNN for the horizontal task of data acquisition in AIoT, propose the unified GNN pipeline based on encoder–decoder paradigm, and systematically categorize and summarize the emerging technologies helpful to address the issues in AIoT data acquisition, especially the noisy and adversarial data, and point out some future directions about GNN‐based AIoT data acquisition.

show abstract

Learning Loss for Active Learning

Cited by 504 publications

References 48 publications

Semisupervised graph convolutional network for hyperspectral image classification

Semisupervised graph convolutional network for hyperspectral image classification

Visual Sentiment Analysis With Active Learning

Artificial intelligence of things (AIoT) data acquisition based on graph neural networks: A systematical review

Contact Info

Product

Resources

About