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 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
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.
Ranked #2 on Semantic Segmentation on PASCAL VOC 2012 test
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.
Ranked #4 on Retinal OCT Disease Classification on OCT2017
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)
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.
Ranked #13 on Semantic Segmentation on PASCAL VOC 2012 val
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.
Ranked #2 on Pedestrian Attribute Recognition on UAV-Human
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
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.
Ranked #35 on Semantic Segmentation on PASCAL VOC 2012 test
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.