Tagged articles
Data Augmentation
76 articles · Page 1 of 1
HiDream.ai's new embodied world model HiDream-O1-Embodied achieves first place on the RoboColiseum robustness benchmark with a 0.692 score, demonstrating superior language understanding, multi-view visual perception, and fault tolerance through a native multimodal architecture and a novel 'real base + generative augmentation' data paradigm, completing the company's unified world model matrix.
Data AugmentationEmbodied AIHiDream-O1-Embodied
0 likes · 12 min read

Xiaomi‑Robotics‑U0, a 38‑billion‑parameter multimodal autoregressive model, unifies four embodied generation tasks, offers geometry‑preserving data augmentation, achieves an 83× inference speedup with FlashAR+, tops the WorldArena benchmark, and improves real‑robot OOD task completion by over 26%.
Data AugmentationEmbodied GenerationFlashAR+
0 likes · 10 min read

The paper proposes Memory‑Guided Hard Data Augmentation (MGHDA), a closed‑loop pipeline that diagnoses model‑specific hard instances in multimodal named entity recognition, abstracts their error patterns into a Memory Tree, and generates targeted augmentation samples, achieving consistent F1 gains across several backbones while highlighting cost and scalability trade‑offs.
AIData AugmentationLLM
0 likes · 15 min read

The paper presents Mechanistic Data Attribution, a framework that traces the origins of specific internal mechanisms such as induction heads to particular training samples, revealing that repetitive "garbage" data—not high‑quality text—drives their emergence, and validates this causal link through deletion and augmentation experiments while enabling scalable data‑driven model improvement.
Causal InterventionData AugmentationInduction Heads
0 likes · 12 min read

The article analyzes Baidu's DuIVRS-2, an end‑to‑end large‑scale interactive voice‑response system for POI data collection, detailing its architectural innovations, data‑augmentation, low‑latency LLM management, dual‑model iterative learning, engineering optimizations, and extensive offline and online experiments that demonstrate superior accuracy, speed, and cost efficiency over prior solutions.
Data AugmentationIVRLLM
0 likes · 18 min read

The article examines the challenges of augmenting time-series forecasting, reviews mainstream techniques—including frequency-domain, decomposition, and patch-based methods—and demonstrates through extensive experiments that Temporal Patch Shuffle (TPS) consistently achieves superior performance across long-term, short-term, and classification tasks.
Data AugmentationTemporal Patch Shufflefrequency domain
0 likes · 20 min read

A German‑French team introduced genESOM, a generative AI model that decouples structure learning from data synthesis, restores lost lipid signals in reduced‑sample multiple sclerosis studies, controls false‑positive inflation, and cuts required preclinical animal numbers by 30‑50% while outperforming GMM and CT‑GAN.
Data AugmentationGenerative AIanimal reduction
0 likes · 12 min read

This article reviews why classic classification augmentations fail for forecasting, introduces the essential data‑label consistency requirement, and systematically categorizes effective time‑series augmentation methods—including frequency‑domain (RobustTAD, FreqMask, FreqMix), decomposition (STAug), and patch‑based approaches (WaveMask, WaveMix, Dominant Shuffle, Temporal Patch Shuffle)—backed by extensive experiments on long‑term, short‑term, and classification tasks.
Data AugmentationTemporal Patch Shufflefrequency domain
0 likes · 20 min read

The article reviews why classic classification augmentations fail for forecasting, outlines a taxonomy of effective time‑series augmentation techniques—including frequency‑domain, decomposition, and patch‑based methods—details the Temporal Patch Shuffle (TPS) pipeline, and presents extensive experiments showing TPS achieves state‑of‑the‑art improvements across long‑term, short‑term, and classification tasks.
Data AugmentationMachine LearningTemporal Patch Shuffle
0 likes · 17 min read

This notebook walks through a complete pipeline—from configuring Isaac Lab Arena environments and downloading datasets, to using Mimic for large‑scale data augmentation, fine‑tuning a GR00T‑N1.5 policy, and performing closed‑loop evaluation—demonstrating how to develop and validate embodied AI tasks on PAI‑DSW.
Data AugmentationGR00TIsaac Lab
0 likes · 14 min read

This article details a data‑flywheel framework for training compact agentic language models, describing synthetic task generation, mock environment simulation, rubric‑based reward design, iterative hard‑sample augmentation, and experimental results that show consistent performance gains across benchmarks.
Data AugmentationReward DesignSynthetic Environments
0 likes · 17 min read

Visual and vision-language models excel under IID benchmarks but often fail on out-of-distribution data due to shortcut learning; this article examines the problem, explains its causes, and proposes data-level and model-level interventions—including StillMix, FLASH, and SPARCL—to improve OOD robustness.
AI researchData AugmentationModel Design
0 likes · 7 min read

This article analyzes why multimodal large language models often fail to detect small objects, identifies three core bottlenecks, and presents a four‑tiered optimization roadmap—from zero‑cost inference tricks to data augmentation, model fine‑tuning, and engineering safeguards—backed by three real‑world case studies and actionable guidelines.
Data AugmentationInference Optimizationmodel fine-tuning
0 likes · 20 min read

This article reviews a recent paper that proposes a drift‑aware data‑stream system integrating machine‑learning‑based adaptive control into financial data management, introducing a parametric data‑operation module, a gradient‑based bi‑level optimizer, and a curriculum planner to improve model robustness and risk‑adjusted returns in non‑stationary markets.
Data AugmentationQuantitative Financeadaptive data synthesis
0 likes · 18 min read

This paper presents a collaborative framework where a large language model generates high‑quality synthetic samples to augment a lightweight model, dramatically improving few‑shot user‑complaint intent recognition in 5G networks, achieving a 21% boost for rare categories and a 9% overall accuracy gain.
Data AugmentationFew-Shot Learningcomplaint intent detection
0 likes · 27 min read

This tutorial walks through fine‑tuning the complex VLA model GR00T‑N1.5 by collecting human demonstrations, annotating and massively augmenting data with DLC, performing distributed imitation learning, and validating the model through a server‑client DSW setup, complete with code snippets, resource specs, and visual examples.
DSWData AugmentationDistributed Imitation Learning
0 likes · 18 min read

FreRA introduces a lightweight, plug‑in frequency‑refined augmentation that adaptively refines spectral components to preserve global semantics while injecting variance, dramatically improving contrastive learning performance on time‑series classification, anomaly detection, and transfer learning across multiple benchmark datasets.
Contrastive LearningData AugmentationRepresentation Learning
0 likes · 13 min read

This tutorial walks through a complete workflow for building a navigation model using Isaac Sim and MobilityGen to generate synthetic data, applying Cosmos‑Transfer1‑7B for visual data augmentation, training the X‑Mobility model via imitation learning, converting it for ROS2 deployment, and performing software‑in‑the‑loop validation.
AI TrainingData AugmentationIsaac Sim
0 likes · 19 min read

This guide demonstrates an end‑to‑end workflow on Alibaba Cloud PAI that uses the Cosmos world model to replace Isaac simulation for robot action data augmentation, including minimal human demonstrations, prompt‑driven data expansion, rejection sampling, IDM inverse‑kinematics extraction, imitation‑learning fine‑tuning, and model evaluation.
AICosmosData Augmentation
0 likes · 17 min read

This article walks through an end‑to‑end Physical AI workflow on Alibaba Cloud PAI, covering robot teleoperation data collection, Isaac Lab‑based data augmentation and enhancement, imitation‑learning model training, distributed DLC execution, and systematic evaluation across varied visual conditions.
Data AugmentationPhysical AIRobotics
0 likes · 17 min read


JavaEdgeSep 14, 2025 · Artificial Intelligence
Hugging Face AI Sheets lets users employ large language models through a spreadsheet‑like interface to clean, transform, enrich, and generate datasets without writing code, offering both zero‑shot dataset creation and import‑based bulk processing, with optional self‑hosting via Docker for privacy‑sensitive workflows.
AI SheetsData AugmentationDocker deployment
0 likes · 5 min read

Data augmentation, while popular for single-source domain generalization, often induces severe out-of-distribution performance swings during training; the PEER framework combats this by employing dual-model collaboration, entropy regularization, periodic parameter averaging, and dynamic augmentation, achieving state-of-the-art robustness across multiple benchmark datasets.
Data AugmentationMachine LearningOOD robustness
0 likes · 7 min read

This article examines the challenges of imbalanced datasets in machine learning, especially in fields like medical imaging, and provides a detailed analysis of three key techniques—MixUp data mixing, CutMix region replacement, and the Focal Loss function—along with their implementations, advantages, limitations, and practical integration strategies.
CutMixData AugmentationFocal Loss
0 likes · 11 min read

This article explains contrastive learning for visual language models, covering its definition, four‑step workflow, how to choose positive and negative pairs, the difference between supervised and self‑supervised variants, and why the technique is essential for zero‑shot and cross‑modal capabilities.
Contrastive LearningData AugmentationRepresentation Learning
0 likes · 6 min read


Amap TechMay 27, 2025 · Artificial Intelligence
This article explains how Gaode Map leverages lightweight edge TTS models, dual‑autoregressive large‑model data augmentation, and a configurable audio‑processing DAG to enable users to create highly realistic personalized voice packs from just three recorded sentences.
Data AugmentationGaode MapsTTS
0 likes · 8 min read

This guide walks readers through every stage of building high‑quality AI training datasets—from locating open‑source data and defining goals, through collection, annotation, cleaning, large‑scale processing, optional augmentation, and splitting, to validation—using a medical QA example for fine‑tuning DeepSeek‑R1.
AI fine-tuningData AugmentationPython
0 likes · 18 min read


AIWalkerJan 10, 2025 · Artificial Intelligence
This paper presents SiCLIP, a framework that simplifies the Transformer architecture, combines weight‑sharing, multi‑stage knowledge distillation, and a novel pair‑matching loss with synthetic captions to train a competitive CLIP model using only one RTX3090 GPU and 1 TB of storage, achieving state‑of‑the‑art data‑size‑parameter‑accuracy trade‑offs.
CLIPData AugmentationLightweight Training
0 likes · 19 min read

This article details Akulaku’s deployment of large language models across multimodal financial risk‑control scenarios—covering business background, a three‑module intelligent‑agent architecture, concrete tool‑ and planning‑enhancement case studies, and future outlook—demonstrating how LLMs boost efficiency, reduce labeling effort, and enable copilot‑style assistance.
Data AugmentationKYC verificationLarge Language Models
0 likes · 15 min read

This article describes a low‑cost, privacy‑preserving chatbot for logistics that combines data cleaning, large‑model‑based data augmentation, BM25 and vector retrieval, a DNN rerank model, and LLM‑driven answer rewriting to deliver accurate, compliant automated responses.
AIBM25Data Augmentation
0 likes · 11 min read

This article describes a privacy‑preserving, low‑cost logistics QA bot that combines data cleaning, augmentation, BM25 and vector retrieval, a DNN rerank model, and LLM‑based answer rewriting, along with evaluation results and deployment considerations.
Data AugmentationHybrid RetrievalLLM rewriting
0 likes · 11 min read

This guide explains how to reduce the computational cost of large language models by preparing instruction data, optionally augmenting or refining it, deploying teacher and student models on PAI, and performing distillation training with detailed hyper‑parameter settings and sample Python scripts.
AIData AugmentationLLM
0 likes · 21 min read

This article outlines key denoising methods—including data cleaning, augmentation, regularization, adversarial training, and self‑supervised learning—that improve the performance, generalization, and robustness of large neural network and transformer models.
Data AugmentationDenoisingRegularization
0 likes · 5 min read

This article provides a detailed, English-language walkthrough of the HRNet source code, covering how the COCO keypoint dataset is built, the online data‑augmentation techniques applied during training, and the end‑to‑end training and inference procedures for human pose estimation.
Computer VisionData AugmentationDeep Learning
0 likes · 36 min read

The article explains CNN fundamentals—convolution, pooling, and fully‑connected layers—illustrates their implementation for American Sign Language letter recognition, details parameter calculations, demonstrates data augmentation and transfer learning techniques, and highlights how these methods boost image‑classification accuracy to around 92%.
CNNData Augmentationimage recognition
0 likes · 19 min read

The article examines the security challenges introduced by large‑model AIGC, outlines three technical upgrade paths—richer training data, few‑shot model fine‑tuning, and multimodal fusion—and demonstrates practical implementations that dramatically improve detection efficiency, accuracy, and scalability.
AI securityAIGCData Augmentation
0 likes · 24 min read

This article introduces ten popular Python libraries—Augmentor, imgaug, albumentations, nlpaug, textaugment, pytorch‑geometric, audiomentations, nlpaugment, keras‑augment, and OpenCV—that provide powerful image, text, audio, and graph data augmentation techniques to improve model generalization and robustness.
Data AugmentationMachine LearningPython
0 likes · 8 min read

This article introduces a continuous semantic enhancement approach for neural machine translation that overcomes the limitations of discrete data‑augmentation techniques, details the neighbor risk minimization training objective, presents benchmark improvements on ACL‑2022 datasets, and describes practical deployment and fine‑tuning workflows in the Modu community.
Contrastive LearningData Augmentationcontinuous semantic augmentation
0 likes · 19 min read

This article introduces various ChatGPT‑based data‑augmentation techniques for natural language processing, explains how to use prompts for synonym, antonym, homophone, random insertion, deletion, and swapping transformations, and provides concrete example prompts and outputs to illustrate each method.
ChatGPTData AugmentationNLP
0 likes · 15 min read

Facing data scarcity in machine learning, this article explores why large datasets are essential, categorizes missing data and label gaps, and presents practical solutions such as dataset reuse, augmentation, multimodal learning, curriculum learning, semi‑supervised methods, active learning, transfer and meta‑learning to mitigate the problem.
Data AugmentationData ScarcityMachine Learning
0 likes · 19 min read


ELab TeamDec 6, 2022 · Artificial Intelligence
This article introduces Apple’s CreateML tool, explains its supported model types, shows how to prepare and augment data, provides a Node.js script for generating synthetic training sets, and walks through training, testing, and integrating an object‑detection model into an iOS app.
CreateMLData AugmentationObject Detection
0 likes · 17 min read

Meituan's Voice Interaction team tackled the lack of low‑resource language annotations and high optimization costs in SemEval‑2022 Task 10 by leveraging the cross‑lingual XLM‑RoBERTa model together with multi‑task learning and two data‑augmentation strategies, achieving first place in the zero‑shot subtask and second place in the monolingual subtask.
Cross-Lingual TransferData AugmentationStructured Sentiment Analysis
0 likes · 25 min read


AntTechNov 6, 2022 · Artificial Intelligence
This article surveys recent Ant Group research on explainable fraud detection, including constraint‑adaptive rule‑set learning (CRSL), meta‑path guided rule generation (MetaRule), biased sampling for imbalanced ranking, and a semi‑supervised data‑augmentation framework (SDAT) for tabular data, highlighting their motivations, methodologies, deployments, and experimental results.
Data AugmentationGraph Neural Networksconstraint adaptive
0 likes · 18 min read

In this AI Live Stream, two Taobao Technology engineers present how causal representation learning enables unbiased data augmentation and factor‑controllable generation to boost fine‑grained image classification, while also unveiling a real‑time color‑enhancement technique that merges cascaded lookup tables with dynamic neural networks, illustrating modern AI trends and practical deployment strategies.
AI AlgorithmsData AugmentationFine-Grained Classification
0 likes · 4 min read

This article reviews the recent NLPCC 2022 NER competition, explains the evolution of named entity recognition, details the five major modeling paradigms, and describes the winning team’s relation‑classification approach, data‑augmentation strategy, experimental results, and its practical deployment in NetEase Cloud Commerce services.
CompetitionData AugmentationDeep Learning
0 likes · 13 min read

58.com’s NLP senior engineer explains how a recruitment knowledge graph is built—through multi‑dimensional tag systems, tag mining, and relation extraction—and how it enhances bidirectional matching and recommendation efficiency, addressing challenges such as weak expression, cold start, and supply‑demand imbalance.
AIData AugmentationNLP
0 likes · 17 min read

The talk explains how to maximize the value of training data by exploring background on model generalization, automatic data augmentation techniques, denoising strategies, active learning for selecting unlabeled samples, and robust data splitting methods, offering practical guidelines for AI practitioners.
AIActive LearningData Augmentation
0 likes · 16 min read

RapNeRF enhances Neural Radiance Fields for extreme view extrapolation by introducing Random Ray Casting and a Ray Atlas, which together augment training data and store view‑dependent surface features, enabling robust, high‑quality novel‑view synthesis from sparse images and outperforming prior methods on synthetic and real datasets.
Data AugmentationNeRFNeural Rendering
0 likes · 8 min read

FSL++—a RoBERTa‑large‑based few‑shot model enhanced with domain‑adaptive pre‑training, prompt learning, diverse embedding‑level augmentations, and ensemble self‑training—topped the Chinese FewCLUE benchmark, beating human accuracy on news and scientific classification tasks and delivering measurable gains across multiple Meituan product scenarios.
Chinese language understandingData AugmentationFew-Shot Learning
0 likes · 23 min read

This article documents the author’s step‑by‑step journey of building an OCR system for recognizing Chinese characters in a card‑game UI, covering game selection, technical background, data generation, deep‑learning model training with CRNN, real‑image data collection, optimization attempts, and final performance evaluation.
CRNNData AugmentationDeep Learning
0 likes · 15 min read

After the BERT era, this article reviews the limitations of pre‑trained language models for semantic matching, discusses negative‑sample sampling, data‑augmentation techniques, contrastive learning methods such as ConSERT and SimCSE, and practical deployment considerations in vector‑based retrieval systems.
Contrastive LearningData Augmentationpretrained language models
0 likes · 20 min read


Code DAOJan 15, 2022 · Artificial Intelligence
The article explains how Tuun, an open‑source Bayesian‑optimization tool, automatically searches data‑augmentation policies for machine‑learning models, details the setup with Microsoft NNI, provides code and configuration examples, and presents experiments on CIFAR‑10/100 and SVHN showing that Tuun‑generated policies match or surpass expert‑tuned strategies and further improve performance when combined.
AutoMLBayesian optimizationData Augmentation
0 likes · 14 min read


Code DAODec 30, 2021 · Artificial Intelligence
The article presents a new data‑refurbishing technique and the Revamper loading system that cut CPU‑heavy data‑augmentation costs while preserving model generalization, showing up to significant throughput gains for ResNet‑50 on ImageNet without sacrificing accuracy.
CPU overheadDNN trainingData Augmentation
0 likes · 10 min read


ITPUBDec 13, 2021 · Artificial Intelligence
This article explains how data augmentation can alleviate overfitting by artificially expanding limited training sets, outlines common transformation techniques for images, text, and audio, and discusses the method's benefits, practical applications, and inherent limitations for machine‑learning practitioners.
Computer VisionData AugmentationDeep Learning
0 likes · 6 min read

The article provides a comprehensive technical overview of PaddleOCR's PP‑OCRv2, detailing its five major algorithmic enhancements, performance improvements over previous versions, historical milestones, core capabilities, and links to the open‑source repositories for developers interested in state‑of‑the‑art OCR solutions.
Computer VisionData AugmentationOCR
0 likes · 10 min read

Meituan’s NLP team leverages few‑shot learning—using data‑augmentation, semi‑supervised, ensemble/self‑training, and domain‑adaptation techniques—to cut annotation costs, achieving 1–2 percentage‑point accuracy gains on internal benchmarks and deploying high‑performing models for tasks such as topic classification, fake‑review detection, and sentiment analysis, while planning broader platform and model extensions.
Active LearningData AugmentationFew-Shot Learning
0 likes · 29 min read


58 TechAug 19, 2021 · Artificial Intelligence
This article presents a comprehensive case study of applying named‑entity‑recognition (NER) techniques to the smart chat assistant of 58.com’s yellow‑page service, covering business background, model selection (BiLSTM‑CRF, IDCNN‑CRF, BERT), data‑augmentation, focal loss, fusion of rule‑based and neural methods, context modeling, online performance, and future research directions.
BERTCRFData Augmentation
0 likes · 16 min read

The article summarizes two INTERSPEECH 2021 papers from Beike's voice technology team, detailing a grammar‑based semantic data augmentation method that improves end‑to‑end Chinese speech recognition and introducing GigaSpeech, a massive 10,000‑hour multilingual English speech dataset for robust ASR research.
ChineseData AugmentationGigaSpeech
0 likes · 7 min read

This article presents Didi's exploration of few‑shot learning, data‑augmentation, semi‑supervised self‑training and multi‑task learning techniques to address the scarcity of labeled samples in safety and governance scenarios, demonstrating practical solutions and performance gains across various risk‑detection tasks.
AIData AugmentationFew-Shot Learning
0 likes · 15 min read


Didi TechApr 20, 2021 · Artificial Intelligence
To overcome scarce labeled data for safety and governance, Didi combines few‑shot learning with systematic data augmentation, self‑training semi‑supervised labeling, and multi‑task neural architectures, cutting labeling costs and reducing log‑loss by over 20% while boosting ROC‑AUC and PR‑AUC across harassment detection, expense‑complaint, and route‑intercept use cases.
AI safetyData AugmentationDidi
0 likes · 15 min read

The article reviews the Chinese NLP pre‑training model generalization competition, detailing data preprocessing, augmentation, external data usage, model scaling and architecture tweaks, loss functions, learning‑rate and adversarial training strategies, regularization techniques, post‑processing optimizations, and ineffective methods, highlighting their impact on performance metrics.
Data AugmentationLoss FunctionsNLP
0 likes · 15 min read


AntTechMar 3, 2021 · Artificial Intelligence
The article presents a comprehensive overview of Ant Group's intelligent service research, summarizing recent AI‑focused papers on text classification, stance detection, data augmentation, knowledge distillation for ranking, reinforcement‑learning‑based dialogue clarification, behavior‑cloning dialogue systems, anti‑fraud outbound bots, tag‑based service recommendation, and multi‑agent service groups, while also highlighting future directions and recruitment opportunities.
AI researchAnti‑fraudData Augmentation
0 likes · 17 min read

This article presents a comprehensive study on automatically extracting theme‑based recommendation reasons for travel content, detailing a three‑stage retrieval framework, the advantages of interactive matching models over classification, rule‑based and back‑translation data augmentation techniques, and various model optimization strategies including priors, transfer learning, seed selection, optimizer choice, and layer‑wise learning rates.
AIData Augmentationmatching models
0 likes · 19 min read

The article outlines a machine‑learning pipeline for automated captcha recognition, covering dataset generation, image preprocessing, segmentation via clustering or watershed methods, and classification using classic models and CNNs, achieving roughly 94% accuracy while noting the growing complexity of modern captchas and recommending developer collaboration when feasible.
CAPTCHAData AugmentationMachine Learning
0 likes · 23 min read

This lecture details the end‑to‑end AI architecture for unmanned stores, covering algorithm module selection, calibration, face recognition, multi‑task detection, tracking, recommendation, data collection, augmentation, model training, and GPU‑accelerated deployment to achieve real‑time performance and high accuracy.
Data AugmentationDeep Learningmodel deployment
0 likes · 15 min read

To enhance object detection robustness, the article discusses various data augmentation methods—including rotation, flipping, random cropping, scaling, color jitter, blurring, transparency adjustment, and image partitioning—providing code examples and illustrating their impact on model performance with before‑and‑after results.
Computer VisionData AugmentationMachine Learning
0 likes · 7 min read

This article describes a practical workflow for expanding a limited industrial solar‑panel defect dataset using flip augmentation, ModelArts smart labeling, and targeted data‑balancing techniques, then evaluates the impact on a ResNet‑50 classifier with detailed accuracy and recall metrics, demonstrating how thoughtful augmentation can improve defect detection performance.
Data AugmentationDeep LearningModelArts
0 likes · 10 min read

This article investigates the practical performance of Google’s 2019 Unsupervised Data Augmentation (UDA) framework on real‑world financial text classification tasks, detailing experiments with limited labeled data, domain‑out‑of‑distribution samples, noisy labels, and comparisons between BERT and lightweight TextCNN models.
BERTData AugmentationFinancial NLP
0 likes · 21 min read

This article explains traditional image augmentation techniques focusing on geometric transformations such as translation and rotation, describes forward and backward mapping concepts, coordinate‑system conversion, matrix representations, and provides detailed C++ OpenCV examples for implementing these operations with warpAffine and getRotationMatrix2D.
C++Data AugmentationGeometric Transformation
0 likes · 11 min read

This comprehensive guide walks front‑end developers through preparing hardware and OS, installing Python and Node environments, launching Pipcook's visual board, running handwritten digit and image classification experiments, creating and augmenting training samples, configuring pipelines, training models, and understanding deployment, all using the Pipcook framework.
Data AugmentationMachine Learningimage classification
0 likes · 34 min read

This article systematically reviews recent developments in text data augmentation for natural language processing, covering common scenarios such as low‑resource and imbalanced classification, and detailing five major techniques—including back‑translation, EDA, TF‑IDF‑based replacement, contextual augmentation, and language‑model‑based methods—with experimental results and future directions.
Data AugmentationMachine LearningNLP
0 likes · 27 min read

The study enhances UI2CODE’s ability to detect tiny UI components by augmenting training data with copied small objects, upgrading the detector from Faster RCNN to FPN and Cascade FPN, and refining box positions with smoothing and projection, achieving superior small‑object mAP/mAR and enabling broader UI parsing applications.
Computer VisionData AugmentationFPN
0 likes · 9 min read


ITPUBOct 22, 2019 · Artificial Intelligence
This guide explains how Keras ImageDataGenerator performs on‑the‑fly image augmentation—covering rotation, shifts, brightness, shear, zoom, channel shifts, flips, and fill‑mode options—with concise Python code examples and visual results to help prevent overfitting in deep‑learning models.
Data AugmentationImageDataGeneratorKeras
0 likes · 7 min read

To solve the shortage of annotated UI data for UI2CODE, the team uses Puppeteer to load Weex pages, traverses the DOM to gather text and image elements, records their styles and positions, screenshots the page, and repeatedly swaps content, automatically generating thousands of realistic, labeled UI samples from a few hundred templates, greatly cutting manual labeling effort and boosting model accuracy.
Data AugmentationPuppeteerSynthetic Samples
0 likes · 8 min read

This article surveys the rapid proliferation of BERT-based research over the past six months, analyzing its impact on various NLP tasks such as question answering, information retrieval, dialog systems, summarization, data augmentation, classification, and sequence labeling, while also discussing the model's strengths, limitations, and future research opportunities.
BERTData AugmentationNLP
0 likes · 52 min read

The article details the Travel team's award‑winning solution for the WSDM Cup 2019 fake‑news detection task, describing data analysis, preprocessing, label‑propagation augmentation, a BERT‑based baseline, a three‑stage multi‑level model‑fusion framework, experimental results, and future directions.
BERTData AugmentationMachine Learning
0 likes · 12 min read

Suning’s face recognition solution combines front‑end detection, optimal photo selection, alignment, and cloud‑based feature extraction and matching, leveraging deep‑learning models, weight and feature normalization, angular margins, and triplet loss, while optimizing hardware, bandwidth, and data quality for large‑scale 1:N deployments.
Data AugmentationDeep Learningface recognition
0 likes · 18 min read
