Method

Image segmentation

Semantic or instance segmentation (U-Net, DeepLab).

23 cases from 18 companies apply Image segmentation. 3 report results in production. Includes variants: Instance segmentation, U-Net.

Typical tasks: Detect anomalies, Evaluate models, Match entities, Optimize decisions and 4 more. Companies: Instacart, LY Corporation, HSE University, Yandex, Sber, Skoltech and 12 more. Often combined with: U-Net, Data augmentation, Image classification, Classical computer vision, Instance segmentation and 53 more.

Making Industrial CV Fly on Edge CPUs: A Neuro-Symbolic Benchmark for Dense Instance Segmentationmanufacturing2026-05
A Digital Core Documentermanufacturing2026-05
Digital Twins of the Heart and Speeding Them Uphealthtech2026-05
From print to digital: Making weekly flyers shoppable at Instacart through computer vision and LLMsretail2026-02
Choosing an automatic quality metric for inpainting models by correlation with human ratingssocial2025-06
Science Like Industry. MLOps for the effective R&D development and deployment of computer vision models in industrial environmentsmanufacturing2025-05
CyberFarm: How We Teach AI to Monitor Cowsmanufacturing2025-05
Improving Aerial Imagery Interpretation with Diffusion Networksmanufacturing2025-05
Automatic Phase Identification in Silicon Carbide Ceramics from Micrographs Using U-Netmanufacturing2025-05
Gigabytes of Nightmares: Turning the Maze of Ultra-Large Medical Images into a Path to Success in Eosinophilic Esophagitishealthtech2025-05
Product ML: Expectations vs. Reality. How to Describe the Organization in Briefgeneral2024-05
Diving into Mystical Depths: Solving the Geonavigation Task Using Metric Learning and Computer Vision in the Oil and Gas and Mining Industriesmanufacturing2023-10
Speeding Up PET/CT Scans with Deep Learning Denoisinghealthtech2023-05
Opportunities for Automating Retinal OCT Image Analysishealthtech2023-05
Modeling the Behavior of an Oil Spillmanufacturing2023-05
Diagnosing Oil and Gas Pipelines Using Machine Learning—manufacturing2023-05
A Guide to Active Learning in CV: Saving on Labeling and Getting a Quality Modelgeneral2023-05
A Review of Artifacts in Histopathology Images—healthtech2023-05
A Gallop Through Production Sites: ML at Nornickelmanufacturing2023-05
Generation of three-dimensional synthetic data for training neural networksgeneral2022-10
What is good for a doctor is death for an engineer: extra requirements for medical AI services—healthtech2022-10
What is good, what is bad. Quality of X-ray images—healthtech2022-10
Detecting the sources of atrial fibrillationhealthtech2022-06