Rethinking Atrous Convolution for Semantic Image Segmentation

17 Jun 201725 code implementations

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.

SEMANTIC SEGMENTATION

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

ECCV 2018 29 code implementations

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.

 SOTA for Semantic Segmentation on PASCAL VOC 2012 test (using extra training data)

IMAGE CLASSIFICATION LESION SEGMENTATION SEMANTIC SEGMENTATION

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

2 Jun 201622 code implementations

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

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

2 Nov 201541 code implementations

We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.

LESION SEGMENTATION REAL-TIME SEMANTIC SEGMENTATION SCENE SEGMENTATION SCENE UNDERSTANDING

DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

CVPR 2019 3 code implementations

A strong baseline is proposed, called Match R-CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner.

POSE ESTIMATION SEMANTIC SEGMENTATION

A Probabilistic U-Net for Segmentation of Ambiguous Images

NeurIPS 2018 7 code implementations

To this end we propose a generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses.

DECISION MAKING SEMANTIC SEGMENTATION