About

Semantic segmentation, or image segmentation, is the task of clustering parts of an image together which belong to the same object class. It is a form of pixel-level prediction because each pixel in an image is classified according to a category. Some example benchmarks for this task are Cityscapes, PASCAL VOC and ADE20K. Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU) and Pixel Accuracy metrics.

( Image credit: CSAILVision )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Libraries

Subtasks

Datasets

Greatest papers with code

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

ECCV 2018 tensorflow/models

The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information.

IMAGE CLASSIFICATION LESION SEGMENTATION SEMANTIC SEGMENTATION

MobileNetV2: Inverted Residuals and Linear Bottlenecks

CVPR 2018 tensorflow/models

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.

IMAGE CLASSIFICATION OBJECT DETECTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

Rethinking Atrous Convolution for Semantic Image Segmentation

17 Jun 2017tensorflow/models

To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates.

Ranked #6 on Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)

SEMANTIC SEGMENTATION

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

2 Jun 2016tensorflow/models

ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales.

SEMANTIC SEGMENTATION

Deep Residual Learning for Image Recognition

CVPR 2016 tensorflow/models

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

DOMAIN GENERALIZATION FINE-GRAINED IMAGE CLASSIFICATION IMAGE-TO-IMAGE TRANSLATION OBJECT DETECTION PEDESTRIAN ATTRIBUTE RECOGNITION PEDESTRIAN TRAJECTORY PREDICTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION

ParseNet: Looking Wider to See Better

15 Jun 2015tensorflow/models

When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines.

SEMANTIC SEGMENTATION

The surprising impact of mask-head architecture on novel class segmentation

1 Apr 2021tensorflow/models

Within this family, we show that the architecture of the mask-head plays a surprisingly important role in generalization to classes for which we do not observe masks during training.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION