Despite achieving over 95% accuracy on ImageNet, popular models like ResNet, VGG, and EfficientNet can be easily misled by carefully crafted adversarial examples using FGSM, revealing deep learning’s inherent vulnerability and prompting the need for robust defense strategies.
This tutorial walks you through the entire process of creating a browser‑based AI version of the classic "draw‑and‑guess" game, covering model selection, dataset preparation, CNN training with TensorFlow.js, model integration into a Vue front‑end, performance optimizations, and deployment steps.
The paper introduces UniConvNet, a novel convolutional architecture that expands the effective receptive field (ERF) of ConvNets without breaking the asymptotically Gaussian distribution (AGD), achieving superior accuracy‑parameter and accuracy‑FLOPs trade‑offs across image classification, detection, and segmentation benchmarks.
Learn the fundamentals of deep learning by building, training, and evaluating a TensorFlow model that recognizes handwritten digits from the MNIST dataset, covering data preparation, network architecture, activation functions, optimizer choices, model compilation, training loops, evaluation metrics, and visualization of predictions.
DefMamba introduces a multi‑scale backbone, deformable Mamba modules, and a dynamic scanning strategy to preserve image spatial structure, achieving state‑of‑the‑art performance on image classification, object detection, and semantic segmentation benchmarks.
This tutorial walks Java developers through building, training, evaluating, and deploying a CIFAR‑10 image classifier using PyTorch, covering data loading, preprocessing, network definition, loss and optimizer setup, GPU acceleration, model saving, and per‑class accuracy analysis.
This article walks through practical Keras tutorials for image‑based traffic‑sign classification and text‑based sentiment analysis, covering data preparation, preprocessing, model construction, training, evaluation, deployment, and a concise comparison of Keras with TensorFlow and PyTorch.
The article introduces Microsoft’s open‑source Computer Vision Recipes library, describing its purpose, target audience, repository links, supported vision scenarios such as image classification, similarity, detection, key‑point, segmentation, action recognition, multi‑object tracking and crowd counting, and provides guidance on using PyTorch, Azure and GPU resources.
This article explains how AI-driven OCR combined with deep‑learning image classification streamlines ticket, document, and license‑plate verification in freight logistics, detailing system architecture, algorithmic components, and future prospects for unified large‑model OCR solutions.
This article describes how to create a cheap AI image‑classification system that trains a TensorFlow model on a desktop, converts it to TFLite, and runs it on Android phones and Raspberry Pi devices, detailing data preparation, training, deployment, and hardware considerations.
The Scale‑Aware Modulation Transformer (SMT) introduces a lightweight SAM module and an Evolutionary Hybrid Network that together achieve higher accuracy on ImageNet, COCO, and ADE20K while using significantly fewer parameters and FLOPs than existing CNN and Transformer baselines.
This article explains how to leverage computer‑vision techniques and deep‑learning frameworks such as Transformers and TensorFlow to build a complete image‑classification pipeline, covering the underlying RGB and CNN principles, model architecture, data preparation, training, and inference with runnable Python code.
This tutorial walks through the complete process of fine‑tuning a Vision Transformer (ViT) model for 14‑class flower image classification on ModelScope, covering dataset preparation, model loading, training configuration, evaluation, and inference with practical code examples.
This article walks readers through building, training, and evaluating a Vision Transformer (ViT) model for a five‑class flower classification task, providing detailed code snippets, model architecture explanations, training script adjustments, and experimental results that highlight the importance of pre‑trained weights.
This article introduces EasyCV, an open‑source all‑in‑one visual algorithm platform that abstracts diverse data sources, provides SOTA self‑supervised models, and offers ready‑to‑download datasets for image classification, object detection, segmentation, and pose estimation, complete with configuration examples.
This article reviews the evolution of deep‑learning image‑classification networks, surveys attention mechanisms for fine‑grained tasks, describes the CVPR 2022 FGVC9 competition solution using RegNetY and random attention cropping, and discusses its deployment in automotive series recognition along with future challenges.
AI-powered porn detection leverages deep neural networks to classify images, but faces serious hurdles such as visual similarity with benign content, subjective standards of obscenity, and vulnerabilities stemming from training data, making human moderators indispensable for reliable content safety.
AI-based porn detection uses deep neural networks to classify images, but faces tough hurdles such as visual similarity with benign content, subjective standards for nudity, and vulnerabilities from training‑data dependence, meaning human moderators remain essential for reliable safety.
This article describes how a second‑hand e‑commerce company built a fast, modular image‑classification pipeline using small binary classifiers, efficientNet‑b0, and active‑learning‑driven data annotation to detect prohibited items while keeping inference latency under 200 ms and reducing labeling costs dramatically.
This article presents an end‑to‑end AI‑driven visual testing solution for mobile applications, detailing the business pain points, data set construction, CNN‑based model design, training procedures, performance evaluation with ROC and confusion matrices, and future directions for improving defect detection accuracy.
This article explains how to train a convolutional neural network on a remote GPU for image classification, covering convolution, padding, activation, pooling, dropout, flattening, fully‑connected layers, dataset preparation, model definition, training, and prediction using TensorFlow/Keras.
The article presents PaddlePaddle’s PP‑ShiTu‑based smart retail product recognition solution, detailing a complete pipeline—from data preparation and model optimization to low‑latency deployment—that overcomes high‑similarity packaging, rapid SKU changes, and costly retraining, achieving over 98 % Top‑1 recall with 0.2‑second CPU inference.
This tutorial demonstrates how to load the Fashion MNIST dataset, explore and preprocess the images, build and compile a neural network with TensorFlow 2.x, train the model, evaluate its accuracy, and use the trained model to make predictions on clothing images, providing complete Python code examples throughout.
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.
The article details a TensorFlow pipeline for detecting white‑screen screenshots in a WebView, covering data preparation from labeled image folders, a CNN architecture with preprocessing, training and validation steps, model saving, inference usage, and strategies to mitigate over‑fitting.
This article walks through creating a satellite image classification pipeline using PyTorch and a pretrained ResNet34 model, covering dataset preparation, project structure, data loading, model definition, training, validation, loss/accuracy plotting, and inference on new images with detailed code examples and results.
This article provides a curated list of publicly available data query websites, simple universal datasets, large-scale collections, and specialized datasets for machine learning, image classification, text classification, and recommendation systems, offering valuable resources for AI research and data-driven projects.
This article introduces a multimodal advertisement detection framework for WeChat KanKan that decomposes the problem into text, image, and article‑structure dimensions, presents novel models for ad text and image recognition, and describes how sequence classification and visualisation are used to filter severe ad‑spam articles.
This article outlines a multimodal AI framework for detecting pornographic video content by combining image and audio analysis, detailing the challenges of visual and speech-based recognition, describing the DCNet and RANet model architectures, fusion strategies, and reporting experimental accuracy of 93.4% on a 3k test set.
By deploying large‑scale visual AI—including a ResNet‑101 classifier, ArcFace‑trained matching features, clustering‑based sub‑category refinement, and product‑level image indexing—Xianyu’s marketplace dramatically improves image quality, removes duplicates, enhances search relevance and feed diversity, and filters non‑compliant content.
This article details Alibaba's AliMama brand risk identification system, covering the challenges of counterfeit detection, the construction of large‑scale brand datasets, the design of classification, logo detection, and variation models, their optimization, evaluation metrics, and future directions for AI‑driven brand protection.
This article presents a method that replaces traditional manual video frame quality checks with an automated YOLOv5‑based object detection pipeline, detailing data labeling, model training, loss computation, inference code, and experimental results that show higher accuracy than ResNet for classifying black, color‑screen, and normal frames.
This article presents a method that replaces manual visual inspection with an automated YOLOv5‑based object detection pipeline to classify video frames as normal, colorful, or black screens, detailing data annotation, training, loss calculation, inference code, and showing a 97% accuracy improvement over ResNet.
This article walks you through using Baidu EasyDL to quickly create, train, and deploy an image‑classification model that detects whether people are wearing masks, covering everything from data collection to API publishing without writing code.
This article analyses the drawbacks of using fully‑connected layers in convolutional neural networks for image tasks, proposes fully‑convolutional alternatives with 1×1 convolutions and strategic max‑pooling, provides TensorFlow code examples, compares model sizes and performance, and discusses deployment considerations for variable‑size inputs.
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.
This guide walks you through setting up Anaconda, preparing UI component images, training a SimpleVGGNet model on macOS, and deploying the model as a Docker‑based service that can be queried via an HTTP API.
This guide walks you through preparing data, configuring a Pipcook pipeline, training a TensorFlow MobileNet model, and using the resulting model to automatically recognize frontend UI components such as buttons, charts, and tables from screenshots.
NBDT (Neural‑Backed Decision Trees) merges a pretrained CNN with a WordNet‑derived hierarchical tree, using the network’s final‑layer weights as class embeddings and a combined classification loss, to deliver state‑of‑the‑art image classification that remains interpretable through explicit hierarchical reasoning.
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.
This tutorial shows how to collect Shiba Inu and Akita images, train a Keras‑based CNN model on TensorFlow, and deploy it as a serverless inference service using Alibaba Cloud Function Compute and the Funcraft tool, turning a simple experiment into a functional breed‑identification web app.
This article presents a complete Python implementation for generating captcha images, loading and preprocessing data, defining a three‑layer convolutional neural network, and training and evaluating the model with TensorBoard, achieving over 99% training accuracy and 93% test accuracy.
The article details Ctrip’s Marco Polo content platform, describing its data, algorithm, and functional layers, and explains how AI techniques such as NLP, semantic matching, named‑entity recognition, and image classification are applied to automate product‑centric content mining, article generation, quality rating, and first‑image selection.
This tutorial walks university students through the complete workflow of using the CIFAR‑10 dataset to train a convolutional neural network for image classification and then deploying the model as an online inference service on the UAI‑Train and UAI‑Inference platforms.
This article describes Alibaba's AI system for automatically filtering nauseating product images on Taobao, covering challenges such as cold‑start, class imbalance, and diverse visual features, and detailing solutions like semi‑supervised learning, active learning, OHEM‑cascade, attention mechanisms, and the resulting business impact.
This article describes 58.com’s deep‑learning‑based advertisement image recognition platform, covering its background, system architecture, QR‑code detection, multi‑scale ResNet classification, category fusion, performance metrics, real‑world case studies, and online service statistics.
Training deep neural networks on large‑scale weakly labeled image data suffers from noisy annotations that degrade performance, but a simple algorithm that adjusts the learning‑rate during training can automatically identify up to 90% of noisy samples, improving dataset cleanliness and model accuracy without manual intervention.
This guide walks you through configuring Huawei Cloud ModelArts, creating an AutoML image‑classification project, labeling cat and leopard photos, training a model, deploying it as an online service, and testing predictions to accurately differentiate between leopards and jaguars.
This article provides a concise introduction to image processing, covering its hierarchical structure, fundamental techniques such as classification, detection, segmentation, geometric transformation, and the most widely used libraries and deep‑learning frameworks for newcomers.
A data scientist from Besedo has open‑sourced a massive NSFW image dataset containing 1.589 million pictures, organized into 159 primary categories and further sub‑categories, with download scripts and GitHub links, requiring about 500 GB of storage and cautioning against viewing in the office.
Data scientist Evgeny Bazarov has open‑sourced a 1.589 million‑image NSFW dataset organized into 159 fine‑grained categories, providing GitHub links, download scripts, and a 500 GB storage requirement, enabling researchers to build more precise adult‑content detection models.
This article introduces TensorFlow, explains when neural networks are appropriate, outlines the general workflow for solving image‑based problems, and provides a step‑by‑step Python implementation of a multilayer perceptron that classifies handwritten digits, while also discussing TensorFlow's strengths, limitations, and alternatives.
This article walks through the Inception v3 TensorFlow codebase, explains its design principles, details the training script flags and loss calculations, shows how to fine‑tune the model on a flower dataset, and provides practical tips for building custom datasets and optimizing hyper‑parameters for image classification.
The article demonstrates how a simple fully‑connected MLP can be trained on a small 64×64×3 cat‑vs‑non‑cat dataset, achieving perfect training accuracy but only 78 % test accuracy, and explains that parameter explosion, vanishing gradients, and lack of spatial invariance limit MLPs, motivating the shift to CNNs.
To address the rising cost of manual UI testing on diverse mobile devices, the article presents a deep‑learning‑based solution using PaddlePaddle that automatically detects UI style bugs such as misaligned controls, text overlap, and blank spaces through data‑driven model training, image preprocessing, and classification.
This article explains the challenges of image‑based porn detection, details the multi‑label classification approach of the Wukong system, and reveals the deep‑learning techniques—including CNN evolution, transfer learning, loss functions, adversarial training, and GAN‑based data augmentation—that enable over 99.5% accuracy with massive daily request volumes.
This article surveys recent breakthroughs in deep learning for computer vision, explains what constitutes an advanced architecture, outlines common vision tasks, and provides concise overviews plus paper and Keras implementation links for ten influential models such as AlexNet, VGG, ResNet, and GAN.
