Tagged articles
image segmentation
30 articles · Page 1 of 1

AIWalkerSep 23, 2025 · Artificial Intelligence
The paper introduces DIDB‑ViT, a high‑fidelity differential‑information‑driven binary Vision Transformer that closes the performance gap with full‑precision models while keeping the original ViT architecture, and demonstrates state‑of‑the‑art results on image classification and ADE20K segmentation, even surpassing full‑precision ResNet‑34.
Edge Deploymentbinary neural networksimage segmentation
0 likes · 28 min read

This article introduces a diffusion‑based framework for salient object detection, discusses its background, challenges, and motivations, details the model architecture and training, presents extensive experiments and ablation studies, and outlines limitations and future research directions.
Computer Visiondeep learningdiffusion model
0 likes · 11 min read


AIWalkerMay 22, 2025 · Artificial Intelligence
VisionReasoner introduces a reinforcement‑learning‑driven unified framework that simultaneously handles detection, segmentation, and counting tasks within a single model, achieving 29.1% higher COCO detection AP, 22.1% better ReasonSeg segmentation, and 15.3% improvement on CountBench, while requiring only 7,000 training samples and offering efficient multi‑target matching via batch computation and the Hungarian algorithm.
LVLMObject CountingObject Detection
0 likes · 19 min read

The article introduces JianYi, a self‑developed image segmentation and matting system for Taobao's home‑decoration business that supports product, human, and panoramic segmentation with multi‑modal interaction, achieving high‑precision real‑time performance and powering AI tools such as "Jiazuo" and "Fang Wo Jia".
Computer Visionartificial intelligencedeep learning
0 likes · 11 min read

This article examines the urgent need for early skin cancer detection in China, outlines the challenges of dermatological imaging, and details a low‑code PaddleX solution that leverages PP‑LiteSeg‑T for data preparation, model training, optimization, and deployment to improve diagnostic accuracy and efficiency.
AIPaddleXSkin Cancer
0 likes · 10 min read

This tutorial explains how to use the open‑source RobustVideoMatting project to perform human portrait segmentation and replace video backgrounds, covering environment setup, model loading, custom image‑and‑video matting functions, and final video composition with OpenCV.
Background ReplacementOpenCVPython
0 likes · 9 min read

This tutorial explains how to use the open‑source RobustVideoMatting project with Python, PyTorch, and OpenCV to perform human portrait segmentation and replace video backgrounds, covering repository setup, model loading, custom segmentation functions, and full video compositing steps.
Background ReplacementOpenCVPyTorch
0 likes · 9 min read

This article explains the fundamentals of image segmentation, introduces the open‑source Segment Anything Model (SAM) and its massive SA‑1B dataset, outlines SAM's unique promptable, real‑time capabilities, and explores its wide‑ranging future applications across AR/VR, content creation, and scientific research.
AIComputer VisionSAM
0 likes · 7 min read

This tutorial explains how to perform image segmentation using the OpenCV library in PHP, covering environment setup, library import, image loading, grayscale conversion, thresholding, result display, and saving the segmented output.
Computer VisionOpenCVPHP
0 likes · 4 min read

This article introduces ModelScope's community‑released visual models, detailing the categorization of understanding versus editing models, the two‑stage coarse‑to‑fine segmentation pipeline for matting, and four editing applications—style transfer, portrait beautification, skin enhancement, and anime‑style conversion—while also previewing upcoming sky‑replacement and video‑matting models.
AIModelScopeimage segmentation
0 likes · 9 min read

This guide shows how to recreate iOS 16’s lock‑screen Depth Effect by integrating Apple’s pre‑trained DeeplabV3 CoreML model with Vision, running a VNCoreMLRequest on a resized image in a background thread, converting the output to a binary mask, and overlaying it on the original photo to simulate foreground‑background depth, with code examples and GitHub source.
CoreMLDepth EffectSWIFT
0 likes · 7 min read

The Kuaishou audio‑video team designed a high‑precision, low‑latency intelligent danmu‑blocking system that uses advanced image‑segmentation and temporal‑stability techniques to generate accurate masks, improve scene robustness, eliminate mask delay, and enhance user experience across diverse video content.
AIKuaishoudanmu blocking
0 likes · 10 min read

To prevent dense on‑screen comments from obscuring key video content, Kuaishou’s audio‑video team built a high‑precision, low‑latency intelligent danmu‑blocking system that uses advanced image‑segmentation masks, temporal stability enhancements, SSIM‑based scene detection, and a large‑scale annotated dataset to ensure robust, real‑time protection across diverse video scenarios.
AIData Annotationdanmu blocking
0 likes · 11 min read

This article presents a series of concise Python examples—each under ten lines—demonstrating how to generate QR codes, create word clouds, perform image segmentation, conduct sentiment analysis, detect masks, automate message sending, extract text with OCR, and build a basic number‑guessing game, showcasing the versatility of Python for quick prototyping across AI and utility tasks.
GameOCRQR Code
0 likes · 10 min read

This article introduces a collaborative‑learning based co‑saliency object detection algorithm that incorporates class‑conditioned information during training, dramatically improving the model's ability to distinguish and detect common objects across image groups, and demonstrates its effectiveness through extensive experiments and real‑world applications.
co-saliency detectioncollaborative learningimage segmentation
0 likes · 10 min read

This article introduces Baidu EasyDL's zero‑threshold AI training camp, focusing on an automatic‑driving scene image‑segmentation case study, covering platform features, model selection, data collection, cleaning, annotation, smart labeling, augmentation, deployment, and a live Q&A session.
AI developmentAutonomous DrivingData Annotation
0 likes · 33 min read


58UXDApr 12, 2021 · Artificial Intelligence
This article chronicles 58.com’s journey from a small brainstorming room to a full‑scale AI design platform, detailing the development of smart cutout, the BASNet segmentation model, custom loss functions, template editing, and the measurable business impact of the AI designer.
AI designBASNetComputer Vision
0 likes · 15 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 AugmentationPython
0 likes · 23 min read


21CTOMay 20, 2020 · Artificial Intelligence
This tutorial shows how to install PaddlePaddle and PaddleHub, then use a concise Python script to batch‑remove backgrounds from multiple photos, automatically saving the segmented results, and includes sample code and before‑after images to illustrate the process.
PaddlePaddlePythonbatch processing
0 likes · 5 min read


ITPUBMay 15, 2020 · Artificial Intelligence
This guide shows how to install PaddlePaddle and PaddleHub, then use a short Python script to automatically segment and remove backgrounds from multiple photos, turning each into a transparent PNG with just a few lines of code.
PaddlePaddlebatch processingimage segmentation
0 likes · 5 min read

This tutorial demonstrates how to use Python and the PaddlePaddle deep‑learning platform to automatically remove backgrounds from multiple photos in one step, covering installation, verification, and a concise five‑line code example for batch human segmentation.
Computer VisionPaddlePaddlebatch processing
0 likes · 6 min read

Ren Haibing, Alibaba’s senior algorithm expert, explains how deep‑learning AI matting—combining salient object detection, semantic and instance segmentation in a two‑stage hard‑then‑soft pipeline—replaces traditional methods, achieves hair‑level detail and temporal consistency, scores 84.3% on Cityscapes, powers large‑scale video‑person extraction, and relies on human review to meet growing industry demand.
AIAlibabaimage segmentation
0 likes · 10 min read

Alibaba's DAMO Academy details its AI‑driven image cutout system, describing why automated matting is needed, the four‑module pipeline (filtering, classification, detection, segmentation), architectural innovations such as dual decoders and fusion networks, and how these advances enable product‑level batch background removal.
AIAlibabaComputer Vision
0 likes · 9 min read

Alibaba's DAMO Academy presents an AI‑driven image cutout system that combines filtering, classification, detection, and advanced segmentation to automate high‑precision matting, improve design efficiency, and unlock new commercial opportunities across e‑commerce and media industries.
AI mattingAlibabaComputer Vision
0 likes · 8 min read


Amap TechDec 13, 2019 · Artificial Intelligence
Gaode Maps has progressed image segmentation from early heuristic region splitting to modern deep‑learning pipelines—leveraging FCNs, multi‑task networks, Mask R‑CNN, and specialized losses—to achieve centimeter‑level, instance‑aware mapping of roads, signs, and small objects while pursuing lighter, real‑time models.
AIComputer VisionGaode Maps
0 likes · 14 min read

The talk outlines how Tencent Advertising leverages deep‑learning visual algorithms—including GCN‑based edge refinement, template generation, AutoML‑driven smart review, and a dual‑tower click‑through‑rate model—to automate creative production, improve ad quality, and enhance user experience across creation, review, and playback stages.
AIAdvertisingAutoML
0 likes · 7 min read

This article explores how deep‑learning‑based image dewarping techniques, from traditional hardware methods to modern U‑Net, Stacked U‑Net and Dilated U‑Net architectures, can correct warped document photos, improve OCR accuracy, and support intelligent verification in high‑throughput business scenarios.
Dilated ConvolutionModel EvaluationOCR
0 likes · 19 min read

Meituan’s AI‑driven system automates banner creation by extracting material features, sequencing them with a planner, refining layouts via an optimizer, and rendering images with a generator, while supporting segmentation, template expansion, and multi‑resolution adaptation to reduce designers’ repetitive work and enable mass personalization.
AIGenerative Modelsbanner design
0 likes · 21 min read

This article presents a step‑by‑step solution that combines computer‑vision preprocessing, OCR, CNN classification, shape matching, and inpainting to isolate meaningful foreground elements from images with intricate backgrounds, discussing practical results, limitations, and code implementations.
Computer VisionOpenCVTensorFlow
0 likes · 15 min read

This article explains how Suning’s intelligent design platform automates banner creation for online retail by combining deep‑learning image segmentation, rule‑based layout generation, multi‑task evaluation models, and adaptive coloring, dramatically reducing manual effort while boosting personalization and conversion rates.
AIautomationbanner design
0 likes · 17 min read
