Pre-trained Deep Neural Network Research Articles

Ensemble learning based lung and colon cancer classification with pre-trained deep neural networks

Ensemble learning based lung and colon cancer classification with pre-trained deep neural networks

Neuroscientific insights about computer vision models: a concise review.

The development of biologically-inspired computational models has been the focus of study ever since the artificial neuron was introduced by McCulloch and Pitts in 1943. However, a scrutiny of literature reveals that most attempts to replicate the highly efficient and complex biological visual system have been futile or have met with limited success. The recent state-of the-art computer vision models, such as pre-trained deep neural networks and vision transformers, may not be biologically inspired per se. Nevertheless, certain aspects of biological vision are still found embedded, knowingly or unknowingly, in the architecture and functioning of these models. This paper explores several principles related to visual neuroscience and the biological visual pathway that resonate, in some manner, in the architectural design and functioning of contemporary computer vision models. The findings of this survey can provide useful insights for building futuristic bio-inspired computer vision models. The survey is conducted from a historical perspective, tracing the biological connections of computer vision models starting with the basic artificial neuron to modern technologies such as deep convolutional neural network (CNN) and spiking neural networks (SNN). One spotlight of the survey is a discussion on biologically plausible neural networks and bio-inspired unsupervised learning mechanisms adapted for computer vision tasks in recent times.

Probing the link between vision and language in material perception using psychophysics and unsupervised learning.

We can visually discriminate and recognize a wide range of materials. Meanwhile, we use language to describe what we see and communicate relevant information about the materials. Here, we investigate the relationship between visual judgment and language expression to understand how visual features relate to semantic representations in human cognition. We use deep generative models to generate images of realistic materials. Interpolating between the generative models enables us to systematically create material appearances in both well-defined and ambiguous categories. Using these stimuli, we compared the representations of materials from two behavioral tasks: visual material similarity judgments and free-form verbal descriptions. Our findings reveal a moderate but significant correlation between vision and language on a categorical level. However, analyzing the representations with an unsupervised alignment method, we discover structural differences that arise at the image-to-image level, especially among ambiguous materials morphed between known categories. Moreover, visual judgments exhibit more individual differences compared to verbal descriptions. Our results show that while verbal descriptions capture material qualities on the coarse level, they may not fully convey the visual nuances of material appearances. Analyzing the image representation of materials obtained from various pre-trained deep neural networks, we find that similarity structures in human visual judgments align more closely with those of the vision-language models than purely vision-based models. Our work illustrates the need to consider the vision-language relationship in building a comprehensive model for material perception. Moreover, we propose a novel framework for evaluating the alignment and misalignment between representations from different modalities, leveraging information from human behaviors and computational models.

Feature-level Fusion vs. Score-level Fusion for Image Retrieval Based on Pre-trained Deep Neural Networks

Today’s complex multimedia content made retrieving images similar to the user’s query from the database a challenging task. The performance of a Content-Based Image Retrieval System (CBIR) system highly depends on the image representation in a form of low-level features and similarity measurement. The traditional visual descriptors that do not provide good prior domain knowledge could lead to poor performance retrieval results. On the other hand, Deep Convolutional Neural Networks (DCNNs) have recently achieved a remarkable success as methods for image classification in various domains. Recently, pre-trained deep convolution neural networks on thousands of classes have the ability to extract very accurate and representative features which, in addition to classification, can also be successfully used in image retrieval systems. ResNet152, GoogLeNet and InceptionV3 are some of the effective and successful examples of pre-trained DCNNs recently applied in a computer vision tasks such as object recognition, clustering, and classification. In this paper, two approaches for a CBIR system, namely early fusion and late fusion, have been presented and compared. The early fusion utilizes concatenation of the features extracted by each possible pair of DCNNs, that is ResNet152-GoogLeNet, ResNet152-InceptionV3, and GoogLeNet-InceptionV3, and the late fusion apply CombSum method with Z-Score standardization to combine the score results provided by each DCNN of the aforementioned pairs. In the experiments on a popular WANG dataset it has been shown that late fusion approach slightly outperforms early fusion approach. The best performance of our experiments in terms of Average Precision (AP) for the top 20 results reaches 96.82%.

3-1-3 Weight averaging technique-based performance evaluation of deep neural networks for Alzheimer’s disease detection using structural MRI

Alzheimer’s disease (AD) is a progressive neurological disorder. It is identified by the gradual shrinkage of the brain and the loss of brain cells. This leads to cognitive decline and impaired social functioning, making it a major contributor to dementia. While there are no treatments to reverse AD’s progression, spotting the disease’s onset can have a significant impact in the medical field. Deep learning (DL) has revolutionized medical image classification by automating feature engineering, removing the requirement for human experts in feature extraction. DL-based solutions are highly accurate but demand a lot of training data, which poses a common challenge. Transfer learning (TL) has gained attention for its knack for handling limited data and expediting model training. This study uses TL to classify AD using T1-weighted 3D Magnetic Resonance Imaging (MRI) from the Alzheimer’s Disease Neuroimaging (ADNI) database. Four modified pre-trained deep neural networks (DNN), VGG16, MobileNet, DenseNet121, and NASNetMobile, are trained and evaluated on the ADNI dataset. The 3-1-3 weight averaging technique and fine-tuning improve the performance of the classification models. The evaluated accuracies for AD classification are VGG16: 98.75%; MobileNet: 97.5%; DenseNet: 97.5%; and NASNetMobile: 96.25%. The receiver operating characteristic (ROC), precision–recall (PR), and Kolmogorov-Smirnov (KS) statistic plots validate the effectiveness of the modified pre-trained model. Modified VGG16 excels with area under the curve (AUC) values of 0.99 for ROC and 0.998 for PR curves. The proposed approach shows effective AD classification by achieving high accuracy using the 3-1-3 weight averaging technique and fine-tuning.

Classification of Lung Cancer using Pre-Trained Deep Learning Models

Many Computer Assisted Diagnosis (CAD) systems have been designed and used in recent past for diagnosingdifferenttypes of cancer. Identification of carcinoma at an earlier stage is more important, and it is made possible due to the use modern image processing and deep learning methods.The occurrence of Lung cancer is seen to be increased and Computed Tomography (CT) scan images were utilized in investigation to locate and classify lung cancer, also for determining the severity of those cancer. This study is aimed at employing pre-trained deep neural networks for classification of lung cancer images. A gaussian-based approach is used to segment CT scan images. In this research exploits a transfer learning-based classification method for the chest CT images acquired from Cancer Image Archive and available in the Kaggle platform. Pre- trained models VGG and RESNET were trained using segmented chest CT images, and their performance was evaluated using different optimization algorithms were analyzed. Keywords: Computer Aided Diagnosis, lung cancer, deep learning, CT image, gaussian, transfer learning, pre-trained models, optimization algorithms.

Makeup-Invariant Faces Recognition Using a Pre-Trained Neural Network, Grasshopper Optimization Algorithm, and Random Forest

Makeup-Invariant Face Recognition is a critical area of research that aims to identify and classify manipulated or forged face images in the field of face recognition systems. Advances in deep learning techniques, such as pre-trained neural networks, have shown promising results in this domain. In this paper, a novel approach for detecting manipulated faces is proposed, combining the strengths of pre-trained neural networks, the Grasshopper Optimization (GOA) Algorithm, and Random Forest classifier. The proposed method utilizes the powerful feature extraction capabilities of pre-trained deep neural networks to capture intricate details and patterns in face images. Subsequently, the GOA algorithm is employed to select optimal features. Additionally, the Random Forest classifier is utilized for effective classification of face images and identifying different individuals based on the selected features. By integrating these three algorithms, the proposed approach demonstrates significant improvements in detecting manipulated faces, achieving higher detection rates and lower false positive rates compared to existing state of the art methods. Simulation results on data from 25 different individuals with manipulated face images show an average accuracy of 97.23%, which represents an enhancement over the compared methods.

Application of deep ensemble learning for palm disease detection in smart agriculture

Agriculture has notably become one of the fields experiencing intensive digital transformation. Leveraging state-of-the-art techniques in this domain has provided numerous advantages for agricultural activities. Deep learning (DL) algorithms have proven beneficial in addressing various agricultural challenges. This study presents a comprehensive investigation into applying DL models for palm disease detection and classification in the context of smart agriculture. The research aims to address the limitations observed in previous studies and improve the robustness and generalizability of the results. To achieve this, a two-stage optimization methodology is employed. First, transfer learning and fine-tuning techniques are applied using various pre-trained deep neural network models. The experiments show promising results, with all models achieving high accuracy rates during training and validation. Furthermore, their performance on unseen test data is also assessed to ensure practical applicability. The top-performing models are MobileNetV2 (92.48 %), ResNet (92.42 %), ResNetRS50 (92.30 %), and DenseNet121 (92.01 %). Second, a deep ensemble learning approach is applied to enhance the models' generalization capability further. The best-performing models with different criteria are combined using the ensemble technique, resulting in remarkable improvements in disease detection tasks. DELM1 emerges as the most successful ensemble model, achieving an ROC AUC Score of 99 %. This study demonstrates the effectiveness of deep ensemble learning models in palm disease detection and classification for smart agriculture applications. The findings contribute to advancing disease detection systems and emphasize the potential of ensemble learning. The study provides valuable insights for future research, guiding the application of DL techniques to address critical agricultural challenges and improve crop health monitoring systems. Another contribution is combining various plant diseases and insect pest classes using diverse datasets. A comprehensive classification system is achieved by considering different disease classes and stages within the white scale category, improving the model's robustness.

Improving 18F-FDG PET Quantification Through a Spatial Normalization Method.

Quantification of 18F-FDG PET images is useful for accurate diagnosis and evaluation of various brain diseases, including brain tumors, epilepsy, dementia, and Parkinson disease. However, accurate quantification of 18F-FDG PET images requires matched 3-dimensional T1 MRI scans of the same individuals to provide detailed information on brain anatomy. In this paper, we propose a transfer learning approach to adapt a pretrained deep neural network model from amyloid PET to spatially normalize 18F-FDG PET images without the need for 3-dimensional MRI. Methods: The proposed method is based on a deep learning model for automatic spatial normalization of 18F-FDG brain PET images, which was developed by fine-tuning a pretrained model for amyloid PET using only 103 18F-FDG PET and MR images. After training, the algorithm was tested on 65 internal and 78 external test sets. All T1 MR images with a 1-mm isotropic voxel size were processed with FreeSurfer software to provide cortical segmentation maps used to extract a ground-truth regional SUV ratio using cerebellar gray matter as a reference region. These values were compared with those from spatial normalization-based quantification methods using the proposed method and statistical parametric mapping software. Results: The proposed method showed superior spatial normalization compared with statistical parametric mapping, as evidenced by increased normalized mutual information and better size and shape matching in PET images. Quantitative evaluation revealed a consistently higher SUV ratio correlation and intraclass correlation coefficients for the proposed method across various brain regions in both internal and external datasets. The remarkably good correlation and intraclass correlation coefficient values of the proposed method for the external dataset are noteworthy, considering the dataset's different ethnic distribution and the use of different PET scanners and image reconstruction algorithms. Conclusion: This study successfully applied transfer learning to a deep neural network for 18F-FDG PET spatial normalization, demonstrating its resource efficiency and improved performance. This highlights the efficacy of transfer learning, which requires a smaller number of datasets than does the original network training, thus increasing the potential for broader use of deep learning-based brain PET spatial normalization techniques for various clinical and research radiotracers.

Hybrid two-level protection system for preserving pre-trained DNN models ownership

AbstractRecent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods.

XECG-Beats: an explainable deep transfer learning approach for ECG-based heartbeat classification

Early detection of abnormal heartbeats is of great importance for cardiologists for early diagnosis of cardiac diseases. This will help patients to receive in time diagnosis and prevention. Conventionally, physicians provide cardiac diagnoses by visual examination of electrocardiograms (ECGs). However, this can be a very time consuming and demanding task and, in some cases, may lead to overlooking and wrong diagnosis of life-threatening heart diseases. Therefore, an intelligent model can help to automatically analyze these huge amount of ECGs captured by different devices in clinical practice. A deep transfer learning approach is used to utilize the capability of different trained deep neural networks and to test them on new unseen datasets without the need to fully re-train the model. Two deep neural networks, namely, Visual Geometry Group (VGG) and Residual Network (ResNet) are utilized for classification of ECGs heartbeats. The models are evaluated using two unseen ECG datasets (i.e., SVDB and INCARTDB) by only optimizing their last classification layers. The overall area under curve for receiver operating characteristic (AUCROC) of two VGG and ResNet models are 0.961 and 0.966 on the SVDB dataset, respectively, and both models achieve 0.981 on the INCARTDB. This paper proposes an accurate and explainable model to classify ECG heartbeats into five categories recommended by the ANSI/AAMI standard. The proposed method paves the way to use pre-trained deep neural networks in real-time monitoring of heart patients using ECG data and to help clinicians understand the decision made by the models on each case using an explainable approach.

Automatic rating method based on deep transfer learning for machine translation considering contextual semantic awareness

With the acceleration of globalization, machine translation (MT) plays an increasingly prominent role in cross-language communication. However, how to evaluate the quality of machine translation, especially considering the nuances in different semantic contexts, remains a challenge. This paper proposes an automatic scoring model for machine translation quality based on deep transfer learning, which aims to accurately perceive and evaluate the quality of translated texts in different semantic contexts. Firstly, a pre-trained deep neural network model is used to extract the semantic feature representation of the sentences in the source language and the target language, so as to capture the semantic information of the sentences. Then, deep transfer learning is used to map the semantic features of source language and target language into the shared feature space. By sharing feature space, an effective relationship is established between the semantic representations of two languages, so as to achieve cross-language quality evaluation. The experimental results show that the model has made significant progress in evaluating the quality of machine translation. Compared with traditional methods, this model can evaluate translation quality more accurately and has better generalization ability. The automatic scoring model of machine translation quality based on deep transfer learning not only improves the accuracy and efficiency of machine translation quality assessment, but also provides new ideas and methods for future research.

Anti Face Spoofing System

Face spoofing, the act of using deceptive techniques such as printed photos or digital images to deceive facial recognition systems, poses a significant threat to the security of various applications, including biometric authentication and access control systems. This paper presents a concise yet effective approach to address the challenge of anti-face spoofing using Python within a limited codebase of 50 lines. The proposed solution leverages a combination of image processing techniques and machine learning algorithms to detect and prevent face spoofing attempts. A pre-trained deep neural network model for facial recognition is employed to extract essential facial features. Subsequently, the system utilizes image manipulation detection methods to identify anomalies indicative of face spoofing attacks. The implementation showcases the simplicity and efficiency of the proposed anti-face spoofing technique, demonstrating the potential for integration into real- world applications with minimal computational overhead. The concise Python code enables easy adoption and adaptation for developers aiming to enhance the security of facial recognition systems against face spoofing threats. The experimental results demonstrate the effectiveness of the approach in accurately distinguishing between genuine and spoofed facial images, thereby contributing to the robustness of facial recognition systems in the presence of adversarial attacks. Keywords - Liveness Detection, Presentation Attack Detection, Spoof Detection Algorithms, Biometric Security, Face Recognition Robustness, 3D Face Modeling, Texture Analysis, Deep Learning Anti- Spoofing, Multi-Spectral Imaging, Behavioral Biometrics, Challenge-Response Mechanisms, Optical Flow Analysis, Pulse Detection, Surface Reflectance, Depth Sensing, Motion Analysis, Pattern Recognition, Anti-Spoofing Networks, Temporal Feature Extraction, Anomaly Detection.

Deep Ensemble Learning-Based Sensor for Flotation Froth Image Recognition.

Froth flotation is a widespread and important method for mineral separation, significantly influencing the purity and quality of extracted minerals. Traditionally, workers need to control chemical dosages by observing the visual characteristics of flotation froth, but this requires considerable experience and operational skills. This paper designs a deep ensemble learning-based sensor for flotation froth image recognition to monitor actual flotation froth working conditions, so as to assist operators in facilitating chemical dosage adjustments and achieve the industrial goals of promoting concentrate grade and mineral recovery. In our approach, training and validation data on flotation froth images are partitioned in K-fold cross validation, and deep neural network (DNN) based learners are generated through pre-trained DNN models in image-enhanced training data, in order to improve their generalization and robustness. Then, a membership function utilizing the performance information of the DNN-based learners during the validation is proposed to improve the recognition accuracy of the DNN-based learners. Subsequently, a technique for order preference by similarity to an ideal solution (TOPSIS) based on the F1 score is proposed to select the most probable working condition of flotation froth images through a decision matrix composed of the DNN-based learners' predictions via a membership function, which is adopted to optimize the combination process of deep ensemble learning. The effectiveness and superiority of the designed sensor are verified in a real industrial gold-antimony froth flotation application.

An Intelligent Vehicle Price Estimation Approach Using a Deep Neural Network Model

In recent years, the market for used-vehicle trade in the Kingdom of Saudi Arabia has grown significantly. This is due to the high cost of new vehicles that are not affordable by most buyers and lifting the ban on women drivers. Recently, several online websites for selling vehicles are available with different functions. However, estimating the vehicle price is based on traditional calculation methods, and this is inaccurate in several selling situations, as there are many factors that may affect the vehicle price, and these factors must be taken into consideration when estimating the vehicle’s price. Therefore, there is high demand to develop an automated vehicle price estimation system through adopting artificial intelligence (AI) technologies. Hence, this paper proposes an efficient vehicle price estimation system through developing an efficient deep neural network (DNN) model. The developed DNN model has been trained using a recent collected dataset for used-vehicle prices in the Kingdom of Saudi Arabia. The developed system has been validated using a recent vehicle price dataset, and the obtained results are compared with seven different machine learning models and showed a promising regression accuracy. In addition, we developed a reliable graphical user interface (GUI) for the purpose of allowing the user to estimate the price of any vehicle using the pre-trained DNN model.

Imperceptible backdoor watermarks for speech recognition model copyright protection

As the demand for shared pre-trained deep neural network models continues to rise, safeguarding the intellectual property of models is also increasingly significant. While existing studies predominantly concentrate on protecting pre-trained image recognition models, limited research covers pre-trained speech recognition models. In this paper, we propose the black-box watermark method to authenticate the ownership of speech recognition models. This method can mitigate the risk of unauthorized AI services being created by attackers who gain access to the pre-trained model. Accordingly, we present three watermarking methods: Gaussian noise watermark, extreme frequency Gaussian noise watermark, and unrelated audio watermark. These generated watermarks, embedded into models through training or fine-tuning, exhibit remarkable fidelity and effectiveness, backed by rigorous experimental validation. Furthermore, our experiments reveal that the extreme frequency noise backdoor enhances the robustness of the watermark compared to the Gaussian noise and unrelated audio watermark.

Anchor objects drive realism while diagnostic objects drive categorization in GAN generated scenes

Our visual surroundings are highly complex. Despite this, we understand and navigate them effortlessly. This requires transforming incoming sensory information into representations that not only span low- to high-level visual features (e.g., edges, object parts, objects), but likely also reflect co-occurrence statistics of objects in real-world scenes. Here, so-called anchor objects are defined as being highly predictive of the location and identity of frequently co-occuring (usually smaller) objects, derived from object clustering statistics in real-world scenes, while so-called diagnostic objects are predictive of the larger semantic context (i.e., scene category). Across two studies (N1 = 50, N2 = 44), we investigate which of these properties underlie scene understanding across two dimensions – realism and categorisation – using scenes generated from Generative Adversarial Networks (GANs) which naturally vary along these dimensions. We show that anchor objects and mainly high-level features extracted from a range of pre-trained deep neural networks (DNNs) drove realism both at first glance and after initial processing. Categorisation performance was mainly determined by diagnostic objects, regardless of realism, at first glance and after initial processing. Our results are testament to the visual system’s ability to pick up on reliable, category specific sources of information that are flexible towards disturbances across the visual feature-hierarchy.

From sleep patterns to heart rhythm: Predicting atrial fibrillation from overnight polysomnograms

BackgroundAtrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Given the prevalence of obstructive sleep apnea among AF patients, electrocardiogram (ECG) analysis from polysomnography (PSG) offers a unique opportunity for early AF prediction. Our aim is to identify individuals at high risk of AF development from single‑lead ECGs during standard PSG. MethodsWe analyzed 18,782 single‑lead ECG recordings from 13,609 subjects undergoing PSG at the Massachusetts General Hospital sleep laboratory. AF presence was identified using ICD-9/10 codes. The dataset included 15,913 recordings without AF history and 2054 recordings from patients diagnosed with AF between one month to fifteen years post-PSG. Data were partitioned into training, validation, and test cohorts ensuring that individual patients remained exclusive to each cohort. The test set was held out during the training process.We employed two different methods for feature extraction to build a final model for AF prediction: Extraction of hand-crafted ECG features and a deep learning method. For extraction of ECG-hand-crafted features, recordings were split into 30-s windows, and those with a signal quality index (SQI) below 0.95 were discarded. From each remaining window, 150 features were extracted from the time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1800 features (12 × 150).A pre-trained deep neural network from the PhysioNet Challenge 2021 was updated using transfer learning to discriminate recordings with and without AF. The model processed PSG ECGs in 16-s windows to generate AF probabilities, from which 13 statistical features were extracted. Combining 1800 features from feature extraction with 13 from the deep learning model, we performed a feature selection and subsequently trained a shallow neural network to predict future AF and evaluated its performance on the test cohort. ResultsOn the test set, our model exhibited sensitivity, specificity, and precision of 0.67, 0.81, and 0.3, respectively, for AF prediction. Survival analysis revealed a hazard ratio of 8.36 (p-value: 1.93 × 10−52) for AF outcomes using the log-rank test. ConclusionsOur proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite modest precision, suggesting false positives. This approach could enable low-cost screening and proactive treatment for high-risk patients. Refinements, including additional physiological parameters, may reduce false positives, enhancing clinical utility and accuracy.

A machine learning decision criterion for reducing scan time for hyperspectral neutron computed tomography systems

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections. This results in scan times of several days to acquire hundreds of hyperspectral projections, during which end users have minimal feedback. To address these challenges, a golden ratio scanning protocol combined with model-based image reconstruction algorithms have been proposed. This novel approach enables high quality real-time reconstructions from streaming experimental data, thus providing feedback to users, while requiring fewer yet a fixed number of projections compared to the filtered back projection method. In this paper, we propose a novel machine learning criterion that can terminate a streaming neutron tomography scan once sufficient information is obtained based on the current set of measurements. Our decision criterion uses a quality score which combines a reference-free image quality metric computed using a pre-trained deep neural network with a metric that measures differences between consecutive reconstructions. The results show that our method can reduce the measurement time by approximately a factor of five compared to a baseline method based on filtered back projection for the samples we studied while automatically terminating the scans.

LarvaTagger: manual and automatic tagging of Drosophila larval behaviour.

As more behavioural assays are carried out in large-scale experiments on Drosophila larvae, the definitions of the archetypal actions of a larva are regularly refined. In addition, video recording and tracking technologies constantly evolve. Consequently, automatic tagging tools for Drosophila larval behaviour must be retrained to learn new representations from new data. However, existing tools cannot transfer knowledge from large amounts of previously accumulated data. We introduce LarvaTagger, a piece of software that combines a pre-trained deep neural network, providing a continuous latent representation of larva actions for stereotypical behaviour identification, with a graphical user interface to manually tag the behaviour and train new automatic taggers with the updated ground truth. We reproduced results from an automatic tagger with high accuracy, and we demonstrated that pre-training on large databases accelerates the training of a new tagger, achieving similar prediction accuracy using less data. All the code is free and open source. Docker images are also available. See gitlab.pasteur.fr/nyx/LarvaTagger.jl.