Semi-supervised Annotation Research Articles

Monocular visual anti-collision method based on residual mixed attention for storage and retrieval machines

In the traditional manufacturing industry, the safe operation of storage and retrieval (S/R) machines is vital for efficient automated warehouse management. Recently, deep learning-based monocular vision approaches have emerged as a promising solution for collision avoidance in automated storage and retrieval systems (AS/RS). However, the scarcity of specific datasets and the need for high-performance, lightweight neural network models pose challenges in the AS/RS domain. To address these challenges, this paper introduces a novel workflow for implementing a monocular anti-collision system for S/R machines. A semi-supervised annotation method leveraging a pretrained clustering model is proposed to expedite image collection and classification, resulting in a tailored dataset. Furthermore, the NightMix technique is introduced, combining Grayscale Enhancement and Floating Grid Mix method to enhance dataset diversity and capacity. Notably, a residual attention awareness module is integrated into MobileNet V3 to enhance its feature processing capabilities. Finally, the proposed approaches are validated through extensive experiments involving various design choices. The experimental results demonstrate that our methods are not only computationally efficient but also highly competitive in terms of learning performance.

ESQmodel: biologically informed evaluation of 2-D cell segmentation quality in multiplexed tissue images.

Single cell segmentation is critical in the processing of spatial omics data to accurately perform cell type identification and analyze spatial expression patterns. Segmentation methods often rely on semi-supervised annotation or labeled training data which are highly dependent on user expertise. To ensure the quality of segmentation, current evaluation strategies quantify accuracy by assessing cellular masks or through iterative inspection by pathologists. While these strategies each address either the statistical or biological aspects of segmentation, there lacks a unified approach to evaluating segmentation accuracy. In this article, we present ESQmodel, a Bayesian probabilistic method to evaluate single cell segmentation using expression data. By using the extracted cellular data from segmentation and a prior belief of cellular composition as input, ESQmodel computes per cell entropy to assess segmentation quality by how consistent cellular expression profiles match with cell type expectations. Source code is available on Github at: https://github.com/Roth-Lab/ESQmodel.

Small Samples and Low-Cost Auto-Segmentation Method for Pelvic Organ-at-Risk Segmentation in Magnetic Resonance Images Using Deep-Learning

In radiotherapy, magnetic resonance (MR) imaging has higher contrast of soft tissue, and no radiation compared with computed tomography (CT) scanning. Due to the high-cost of manual annotation, the deep-learning based automatic organ-at-risk (OAR) and target delineation algorithms are in high-demand, but the collecting of large amounts of high-quality annotated datasets remains difficulty. In this paper, we proposed a low-cost OAR segmentation method with semi-supervised annotation using small annotation samples of pelvic MR images. This study consisted of 94 patients diagnosed with rectal cancer from April 2018 to March 2021 at Peking University People's Hospital. We used 17 slices of MR images with annotation and 78 slices without annotation to train a deep-learning based segmentation model. The bladder, femoral heads, rectum and small intestine were selected as OAR. Semi-supervised method and ensemble learning were used for generating training set using small sample with annotation. Post-processing algorithm was used to correct the self-annotation data. Two of 14 annotation samples were set as test set. As for un-labeled images, 40 of them were set as semi-supervised annotation train set, the rest were test set. Besides, both 2D and 3D auto-segmentation networks were evaluated. The dice of bladder, femoral head left and right, rectum and small intestine between segmentation results and reference masks is 0.947, 0.983, 0.981, 0.900, 0.845 only using self-annotation and post-processing method of 2D segmentation model. And the dice of corresponding OAR is 0.871, 0.975, 0.975, 0.783, 0.724 using 3D segmentation network, 0.885,0.982, 0.982, 0.882, 0,814 using 2D segmentation network with supervised method (nnUNet). The 2D model outperformed 3D model with better segmentation performance, shorter inference time and fewer parameters. The results proved that we can train a multi-OAR segmentation model only using small annotation samples and other unlabeled samples. Ensemble learning and post-processing methods are necessary for semi-supervised data annotation. For anisotropy data, 2D model shows better performance than 3D models.

Explicit Aspect Annotation via Transfer and Active Learning

We present a semi-supervised annotation process for identifying and labelling explicit aspects of an initially unlabelled corpus. Firstly, we employ cross-domain learning to pre-annotate the initial data, deliberately excluding domain-related input features to ensure effective learning transfer. Then, we apply an active learning strategy to enhance the pre-annotation performance and enrich the learning data. We adjust the strategy to sequence labeling and address class imbalance. We evaluate this process using two unlabelled datasets in French, consisting of user opinions on beauty products and electronic devices, respectively. The results show an improved F1-score achieved by increasing and correcting 30% of the training dataset.

ScSemiGAN: a single-cell semi-supervised annotation and dimensionality reduction framework based on generative adversarial network.

Cell-type annotation plays a crucial role in single-cell RNA-seq (scRNA-seq) data analysis. As more and more well-annotated scRNA-seq reference data are publicly available, automatical label transference algorithms are gaining popularity over manual marker gene-based annotation methods. However, most existing methods fail to unify cell-type annotation with dimensionality reduction and are unable to generate deep latent representation from the perspective of data generation. In this article, we propose scSemiGAN, a single-cell semi-supervised cell-type annotation and dimensionality reduction framework based on a generative adversarial network, to overcome these challenges, modeling scRNA-seq data from the aspect of data generation. Our proposed scSemiGAN is capable of performing deep latent representation learning and cell-type label prediction simultaneously. Through extensive comparison with four state-of-the-art annotation methods on diverse simulated and real scRNA-seq datasets, scSemiGAN achieves competitive or superior performance in multiple downstream tasks including cell-type annotation, latent representation visualization, confounding factor removal and enrichment analysis. The code and data of scSemiGAN are available on GitHub: https://github.com/rafa-nadal/scSemiGAN. Supplementary data are available at Bioinformatics online.

ScMRA: a robust deep learning method to annotate scRNA-seq data with multiple reference datasets.

Single-cell RNA-seq (scRNA-seq) has been widely used to resolve cellular heterogeneity. After collecting scRNA-seq data, the natural next step is to integrate the accumulated data to achieve a common ontology of cell types and states. Thus, an effective and efficient cell-type identification method is urgently needed. Meanwhile, high-quality reference data remain a necessity for precise annotation. However, such tailored reference data are always lacking in practice. To address this, we aggregated multiple datasets into a meta-dataset on which annotation is conducted. Existing supervised or semi-supervised annotation methods suffer from batch effects caused by different sequencing platforms, the effect of which increases in severity with multiple reference datasets. Herein, a robust deep learning-based single-cell Multiple Reference Annotator (scMRA) is introduced. In scMRA, a knowledge graph is constructed to represent the characteristics of cell types in different datasets, and a graphic convolutional network serves as a discriminator based on this graph. scMRA keeps intra-cell-type closeness and the relative position of cell types across datasets. scMRA is remarkably powerful at transferring knowledge from multiple reference datasets, to the unlabeled target domain, thereby gaining an advantage over other state-of-the-art annotation methods in multi-reference data experiments. Furthermore, scMRA can remove batch effects. To the best of our knowledge, this is the first attempt to use multiple insufficient reference datasets to annotate target data, and it is, comparatively, the best annotation method for multiple scRNA-seq datasets. An implementation of scMRA is available from https://github.com/ddb-qiwang/scMRA-torch. Supplementary data are available at Bioinformatics online.

Multi-label Arabic text classification in Online Social Networks

Online Social Networks (OSNs) are the most popular interactive media for communicating, posting, and sharing indefinite amounts of personal information. However, along with interesting and attractive topics and contents, some users neither like the fact that certain topics that are not among their interests can fill their personal pages nor do they wish to see disappointing negative posts that may appear repeatedly. Also, people sometimes post inappropriate or abusive content on these networks, such as insults or pornography. Most of the efforts in the field of text classification have focused on the English language, while research on the Arabic language, which has numerous challenges is scarce. In this paper, we constructed a standard multi-label Arabic dataset using manual annotation and a semi-supervised annotation technique that can be used for short text classification, sentiment analysis, and multilabel classification. Then, we evaluated the topics classification, sentiment analysis, and multilabel classification. Based on that evaluation we found a relationship between topics published in OSNs and hate speech. The experimental results validate the effectiveness of the proposed technique.

Sentiment analysis on big sparse data streams with limited labels

Sentiment analysis is an important task in order to gain insights over the huge amounts of opinionated texts generated on a daily basis in social media like Twitter. Despite its huge amount, standard supervised learning methods won’t work upon such sort of data due to lack of labels and the impracticality of (human) labeling at this scale. In this work, we leverage distant supervision and semi-supervised learning to annotate a big stream of tweets from 2015 which consists of 228 million tweets without retweets (and 275 million with retweets). We present the insights from our annotation process regarding the effect of different semi-supervised learning approaches, namely Self-Learning, Co-Training and Expectation–Maximization. Moreover, we propose two annotation modes, the batch mode where all labeled and unlabeled data are available to the algorithms from the beginning and a lightweight streaming mode that processes the data in batches based on their arrival time in the stream. Our experiments show that stream processing with a sliding window of three months achieves comparable results to batch processing while being more efficient. Finally, to tackle the class imbalance problem, as our dataset is imbalanced toward the positive sentiment class, and its aggravation by the semi-supervised learning methods, we employ data augmentation in the semi-supervised learning process in order to equalize the class distribution. Our results show that semi-supervised learning coupled with data augmentation outperforms significantly the default semi-supervised annotation process. We make the so-called TSentiment15 sentiment-annotated dataset available to the community to be used for evaluation purposes and for developing new methods.

Semi-supervised annotation of faces in image collection

The objective of this work is to correctly detect and recognize faces in an image collection using a database of known faces. This has applications in photo-tagging, video indexing, surveillance and recognition in wearable computers. We propose a two-stage approach for both detection and recognition tasks. In the first stage, we generate a seed set from the given image collection using off-the-shelf face detection and recognition algorithms. In the second stage, the obtained seed set is used to improve the performance of these algorithms by adapting them to the domain at hand. We propose an exemplar-based semi-supervised framework for improving the detections. For recognition of images, we use sparse representation classifier and generate seed images based on a confidence measure. The labels of the seed set are then propagated to other faces using label propagation framework by imposing appropriate constraints. Unlike traditional approaches, our approach exploits the similarities among the faces in collection to obtain improved performance. We conduct extensive experiments on two real-world photo-album and video collections. Our approach consistently provides an improvement of $${\sim } 4$$ % for detection and $$5{-}9$$ % for recognition on all these datasets.

Optimized Graph Learning Using Partial Tags and Multiple Features for Image and Video Annotation.

In multimedia annotation, due to the time constraints and the tediousness of manual tagging, it is quite common to utilize both tagged and untagged data to improve the performance of supervised learning when only limited tagged training data are available. This is often done by adding a geometry-based regularization term in the objective function of a supervised learning model. In this case, a similarity graph is indispensable to exploit the geometrical relationships among the training data points, and the graph construction scheme essentially determines the performance of these graph-based learning algorithms. However, most of the existing works construct the graph empirically and are usually based on a single feature without using the label information. In this paper, we propose a semi-supervised annotation approach by learning an optimized graph (OGL) from multi-cues (i.e., partial tags and multiple features), which can more accurately embed the relationships among the data points. Since OGL is a transductive method and cannot deal with novel data points, we further extend our model to address the out-of-sample issue. Extensive experiments on image and video annotation show the consistent superiority of OGL over the state-of-the-art methods.

An Iterative Partitioning-Based Method for Semi-Supervised Annotation Learning in Image Collections

Labeling images is tedious and a costly work that is required for many applications, for example, tagging, grouping and exploring of image collections. It is also necessary for training visual classifiers that recognize scenes or objects. It is therefore desirable to either reduce the human effort or infer additional knowledge by addressing this task with algorithms that allow for learning image annotations in a semi-supervised manner. In this paper, a semi-supervised annotation learning algorithm is introduced that is based on partitioning the data in a multi-view approach. The method is applied to large, diverse image collections of natural scene images. Experiments are performed on the 15 Scenes and SUN databases. It is shown that for sparsely labeled datasets the proposed annotation learning algorithm is able to infer additional knowledge from the unlabeled samples and therefore improve the performance of visual classifiers in comparison to supervised learning. Furthermore, the proposed algorithm outperforms other related semi-supervised learning approaches.

Online semi-supervised annotation via proxy-based local consistency propagation

Abstract In this paper, we propose a novel label propagation algorithm named Proxy-based Local Consistency Propagation (PLCP), in which the label information is first propagated from labeled examples to the unlabeled ones, and then spreads only among unlabeled ones mutually until a steady state is reached. To meet the requirements of efficiency in many real-world image annotation applications, we propose an online semi-supervised annotation framework where the new examples can be predicted and used to update the model. Specifically, we extend PLCP to work under an inductive setting and propose an incremental model updating method that can incorporate the new examples including labeled and unlabeled examples. The comprehensive experiments on MNIST, CIFAR-10 and PIE datasets show that our proposed PLCP achieves superior performance compared with the baselines, and our proposed incremental model updating method can achieve significant promotion in efficiency, with the nearly identical accuracy compared to re-training.