Tagged articles
semantic segmentation
34 articles · Page 1 of 1

ITPUBOct 12, 2026 · Artificial Intelligence
This article benchmarks 16 semantic segmentation models—including CNN, Transformer, and Mamba architectures—on the DeepGlobe land cover dataset using a unified training protocol, revealing U-MixFormer-B1 as the fastest-converging model and SegFormer-B1 as the accuracy leader with 0.7438 mIoU, while demonstrating that encoder-decoder matching matters more than backbone strength.
CNNDeepGlobeMamba
0 likes · 15 min read

Chunk splitting, a critical yet often overlooked step in RAG pipelines, dramatically impacts retrieval recall and LLM output quality; this guide walks through three evolution stages—from naive fixed‑length splits to sentence‑aware overlaps and finally semantic, structure‑driven segmentation—complete with code, experiments, and practical pitfalls.
LLMRAGchunking
0 likes · 15 min read

This article introduces the U‑Net architecture—originally designed for medical image segmentation—explains why its pixel‑wise processing makes it the core denoising engine in Stable Diffusion, details three key modifications for diffusion models, and walks through a ResNet‑50‑based implementation trained on the VOC2012 dataset, achieving 0.92 pixel accuracy and 0.64 mean IoU.
PyTorchResNet50Stable Diffusion
0 likes · 11 min read

This article reveals that the conventional threshold/argmax post‑processing for semantic segmentation is sub‑optimal for Dice/IoU metrics, introduces the RankSEG framework that optimizes predictions without retraining, and presents an efficient RankSEG‑RMA approximation with extensive experiments showing consistent performance gains.
Dice optimizationRankSEGdeep learning
0 likes · 12 min read

This article explains how different chunking methods—fixed size, semantic, recursive, document‑based, agent‑driven, sentence‑level, and paragraph‑level—affect Retrieval‑Augmented Generation, offering practical guidelines, metrics, and optimization tips for real‑world deployments.
AIRAGchunking
0 likes · 9 min read

This article reviews the depth‑guided texture diffusion method, detailing its texture extraction, diffusion, structural consistency optimization, and integration into segmentation networks, and shows how it narrows the depth‑RGB gap to achieve state‑of‑the‑art performance on various semantic segmentation tasks.
Computer Visiondepth-guided diffusionsemantic segmentation
0 likes · 13 min read


AIWalkerSep 2, 2025 · Artificial Intelligence
BEVANet tackles the efficiency‑accuracy trade‑off in real‑time semantic segmentation by integrating large‑kernel attention, an efficient visual attention (EVA) module, a bilateral architecture, and boundary‑guided adaptive fusion, delivering up to 81 % mIoU on Cityscapes at 33 FPS and surpassing prior state‑of‑the‑art models on both accuracy and speed.
Computer VisionEfficiencyReal-time
0 likes · 19 min read


AIWalkerJun 18, 2025 · Artificial Intelligence
Nvidia introduces SeNaTra, a native‑segmentation vision transformer that replaces uniform down‑sampling with a content‑aware spatial grouping layer, delivering superior zero‑shot and supervised segmentation performance while cutting parameters and FLOPs compared with Swin Transformer and other backbones.
NVIDIAZero-Shot Learningsemantic segmentation
0 likes · 29 min read


AIWalkerMay 12, 2025 · Artificial Intelligence
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.
Computer VisionDefMambaObject Detection
0 likes · 23 min read

This article presents a novel dual‑optimization distillation framework that injects Segment Anything Model (SAM) semantic priors into multimodal image fusion, achieving unified visual quality and task accuracy while using a lightweight sub‑network to keep inference efficient.
Image FusionSAMlightweight network
0 likes · 11 min read

This article walks through a complete methodology for creating brand symbol posters using AI, covering basic and advanced Stable Diffusion techniques such as ControlNet, depth‑map generation, semantic segmentation, LoRA integration, and post‑processing to achieve high‑quality, efficient visual assets.
AI image generationControlNetDepth map
0 likes · 10 min read

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.
Object DetectionSMThybrid CNN‑Transformer
0 likes · 12 min read

This article introduces DeepLabV2, explains its challenges, architectural enhancements such as the ASPP module, backbone modifications, poly learning‑rate policy, and presents experimental comparisons on several benchmark datasets, providing a concise yet comprehensive overview for computer‑vision practitioners.
ASPPDeepLabV2semantic segmentation
0 likes · 9 min read

Recent advances in visual language models enable zero-shot multimodal tasks, and this article explores their application to open-set object detection, prompt learning, and promptable surgical instrument segmentation, highlighting methods like CLIP, CoOp, and the DetPro framework with experimental results across multiple benchmarks.
Computer Visionmultimodalopen-set detection
0 likes · 12 min read

This article explains the two main challenges of applying deep convolutional neural networks to semantic segmentation—signal down‑sampling and loss of spatial precision—and describes how the DeepLabV1 architecture, using dilated convolutions, large‑field‑of‑view modules, fully‑connected CRF and multi‑scale fusion, addresses these issues while achieving faster, more accurate segmentation results.
CRFDeepLabV1Dilated Convolution
0 likes · 12 min read

Meituan’s Visual Intelligence team recently published eight top‑conference papers that advance weakly supervised segmentation, future‑aware captioning, panoptic narrative grounding, video‑text retrieval, open‑vocabulary detection, counterfactual image‑text matching, zero‑shot video classification, and efficient Vision‑Transformer quantization, all directly boosting real‑world content creation, distribution, and model efficiency.
AI researchImage CaptioningOpen-Vocabulary Detection
0 likes · 19 min read

This tutorial walks through the complete FCN pipeline for semantic segmentation, covering VOC dataset loading, data augmentation, collate functions, model construction, training loops, loss computation with cross‑entropy (including ignore‑index handling), and inference, while providing full PyTorch code snippets for each step.
FCNPyTorchVOC dataset
0 likes · 19 min read

This article provides a comprehensive, beginner‑friendly overview of semantic segmentation, focusing on the pioneering Fully Convolutional Network (FCN) architecture, its variants (FCN‑32s, FCN‑16s, FCN‑8s), underlying concepts, loss computation, and practical tips for working with the VOC dataset.
AlexNetComputer VisionFCN
0 likes · 14 min read

This article explains the role of Youzan’s Query Parser (QP) in search, walks through its overall and layered architecture, details each algorithmic plugin—from preprocessing to synonym handling—and shows concrete code examples and results that improve search relevance across multiple retail scenarios.
NLPYouzanplugin design
0 likes · 12 min read

To enable real‑time bullet‑comment passthrough on Youku’s mobile app, the team built a million‑scale portrait dataset and designed the AirSegNet series—CPU, GPU, and server variants—using VGG‑style nets, edge‑aware losses, and hybrid CPU‑GPU inference, achieving 0.98 IoU and sub‑15 ms latency on most devices.
Computer VisionEdge ComputingMNN Framework
0 likes · 13 min read

Meituan leverages computer‑vision techniques to tag, analyze, and automatically generate short videos across consumer and merchant scenarios, detailing hierarchical tag design, self‑supervised representation learning, fine‑grained food recognition, intelligent cover creation, and pixel‑level editing to enhance content discovery and presentation.
AI Content GenerationComputer VisionSelf-Supervised Learning
0 likes · 20 min read

The article presents a comprehensive AI solution for video danmu (bullet‑screen) occlusion prevention that leverages human portrait semantic segmentation, describes dataset construction with full‑ and semi‑supervised labeling, details the encoder‑decoder model with context attention, outlines post‑processing for spatial and temporal stability, and explains deployment on cloud and edge using YKit, KwaiNN and TensorRT.
AICloud InferenceDanmu
0 likes · 15 min read

The article presents Semantic Image Matting, a novel approach that incorporates 20 semantic Alpha pattern categories into the matting pipeline via semantic Trimap, region‑based classifiers, multi‑class discriminators, and learnable gradient loss, achieving state‑of‑the‑art results on multiple benchmarks.
Computer Visionalpha patternsdeep learning
0 likes · 11 min read

At a CVPR 2021 pre‑lecture, Meituan’s Visual Intelligence Center showcased five cutting‑edge papers—VisTR transformer‑based video instance segmentation, a feature‑decomposition facial expression recognizer, an accelerated BiSeNet for real‑time semantic segmentation, an embedded discriminative attention mechanism for weakly supervised segmentation, and a partial‑feature selection framework for multi‑source domain adaptation—highlighting the company’s large AI R&D team, university collaborations, real‑world deployment across its services, and ongoing recruitment.
AICVPR2021Facial Expression Recognition
0 likes · 10 min read

Learn how to generate cinematic ghosting effects in videos by leveraging PaddlePaddle’s PaddleHub deep learning library and the pretrained deeplabv3p_xception65 model for semantic segmentation, with step‑by‑step code, environment setup, and practical testing on classic martial‑arts footage.
Ghost EffectPaddlePaddlePython
0 likes · 7 min read


Amap TechMar 23, 2020 · Artificial Intelligence
Gaode leverages high‑resolution satellite imagery as an active discovery tool for map updates, extracting road, region and building elements through advanced semantic segmentation networks (U‑Net, ASPP, attention, non‑local) and instance‑segmentation pipelines, to accelerate accurate road‑network and building‑block data refreshes while addressing future scalability challenges.
Computer VisionSatellite ImageryU-Net
0 likes · 11 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


Didi TechMay 1, 2019 · Artificial Intelligence
The DFS face-detection algorithm jointly created by Didi AI Labs and Beijing University's PRIS team secured five first-place and one second-place results on the WIDER FACE benchmark, achieving 96.3% (Easy), 95.4% (Medium) and 90.7% (Hard) AP by leveraging a Feature Fusion Pyramid and semantic-segmentation supervision, and is already deployed in Didi's driver-identity verification and in-vehicle privacy systems.
Feature FusionWIDER FACEsemantic segmentation
0 likes · 5 min read

This article provides an extensive review of deep learning techniques applied to computer vision, covering the evolution of CNN architectures, image and video processing tasks, 2.5‑D and 3‑D reconstruction, object detection, segmentation, tracking, SLAM, and various practical applications such as AR, content retrieval, and autonomous driving.
CNNComputer VisionObject Detection
0 likes · 22 min read

This article introduces Alibaba’s intelligent matting editor and its Semantic Human Matting (SHM) algorithm, detailing the integration of semantic segmentation and deep matting networks, the fusion module, training strategy, experimental results, and the deployment of an online fully‑automatic cutout tool for designers.
Alibabaautomatic cutoutdeep learning
0 likes · 16 min read

This article details how Alibaba’s AliPlayStudio combines advanced computer‑vision algorithms—such as human semantic segmentation, gesture and pose detection, controllable style transfer, and face‑fusion—optimised for low‑power mobile and embedded devices, to deliver engaging real‑time video interactions across online and offline marketing scenarios.
face fusiongesture recognitionmobile AI
0 likes · 17 min read

This article details the research and engineering behind Alibaba's AliPlayStudio, a video‑interactive platform that combines computer‑vision algorithms such as human parsing, gesture and pose detection, and controllable style transfer, all optimized for real‑time deployment on low‑power mobile and embedded devices.
gesture recognitionmobile AIpose estimation
0 likes · 17 min read

iQIYI’s bullet‑screen masking employs a DeepLabv3+‑based two‑class semantic segmentation pipeline, preceded by a close‑up detector and followed by morphological refinement, trained on a custom annotated dataset that raises IoU to 93.6 %, processes hour‑long videos in under an hour, and is slated for future upgrades to instance and panoptic segmentation for finer‑grained masking.
AIbullet screen maskingiQIYI
0 likes · 10 min read

This article traces the evolution of computer vision from its 1960s origins, explains the challenges of image classification and semantic segmentation, and introduces pixel-level decision forest algorithms as an efficient solution for large‑scale pixel classification tasks.
Computer VisionPixel Classificationdecision forest
0 likes · 9 min read
