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

Latest papers without code

Dual Discriminator Adversarial Distillation for Data-free Model Compression

12 Apr 2021

Then the generated samples are used to train the compact student network under the supervision of the teacher.

KNOWLEDGE DISTILLATION MODEL COMPRESSION SEMANTIC SEGMENTATION

Volume and leaf area calculation of cabbage with a neural network-based instance segmentation

12 Apr 2021

Fruit size and leaf area are important indicators for plant health and are of interest for plant nutrient management, plant protection and harvest.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Improving Online Performance Prediction for Semantic Segmentation

12 Apr 2021

In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i. e., during inference, which is of high importance in safety-critical applications such as autonomous driving.

AUTONOMOUS DRIVING MONOCULAR DEPTH ESTIMATION SEMANTIC SEGMENTATION

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

12 Apr 2021

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Ensemble Learning based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for polyp localisation

10 Apr 2021

Based on an observation that different segmentation algorithms will perform well on different subsets of examples because of the nature and size of training sets they have been exposed to and because of method-intrinsic factors, we propose to measure the confidence in the prediction of each algorithm and then use an associate threshold to determine whether the confidence is acceptable or not.

SEMANTIC SEGMENTATION

Two layer Ensemble of Deep Learning Models for Medical Image Segmentation

10 Apr 2021

We propose a two-layer ensemble of deep learning models for the segmentation of medical images.

MEDICAL IMAGE SEGMENTATION SEMANTIC SEGMENTATION

Estimation of BMI from Facial Images using Semantic Segmentation based Region-Aware Pooling

10 Apr 2021

The recent works have either employed hand-crafted geometrical face features or face-level deep convolutional neural network features for face to BMI prediction.

SEMANTIC SEGMENTATION

Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation

10 Apr 2021

Current state-of-the-art object detection and segmentation methods work well under the closed-world assumption.

OBJECT DETECTION OBJECT TRACKING SEMANTIC SEGMENTATION VIDEO UNDERSTANDING YOUTUBE-VOS