1929 papers with code • 51 benchmarks • 185 datasets
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 )
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.
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.
Ranked #1 on Semi-Supervised Video Object Segmentation on YouTube
Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space.
Ranked #7 on Semantic Segmentation on PASCAL VOC 2012 val
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #3 on Human Part Segmentation on PASCAL-Part
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 (using extra training data)
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)