Browse > Computer Vision > Instance Segmentation

Instance Segmentation

43 papers with code · Computer Vision

Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.

State-of-the-art leaderboards

Greatest papers with code

Mask R-CNN

ICCV 2017 tensorflow/models

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection.

HUMAN PART SEGMENTATION INSTANCE SEGMENTATION KEYPOINT DETECTION MULTI-HUMAN PARSING OBJECT DETECTION SEMANTIC SEGMENTATION

Learning to Segment Every Thing

CVPR 2018 facebookresearch/detectron

Most methods for object instance segmentation require all training examples to be labeled with segmentation masks. This requirement makes it expensive to annotate new categories and has restricted instance segmentation models to ~100 well-annotated classes.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Non-local Neural Networks

CVPR 2018 facebookresearch/detectron

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies.

INSTANCE SEGMENTATION KEYPOINT DETECTION OBJECT DETECTION VIDEO CLASSIFICATION

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

CVPR 2018 NVIDIA/pix2pixHD

We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic.

CONDITIONAL IMAGE GENERATION IMAGE-TO-IMAGE TRANSLATION INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Deformable ConvNets v2: More Deformable, Better Results

27 Nov 2018msracver/Deformable-ConvNets

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

A MultiPath Network for Object Detection

7 Apr 2016facebookresearch/multipathnet

The recent COCO object detection dataset presents several new challenges for object detection. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization.

INSTANCE SEGMENTATION OBJECT DETECTION

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

6 Dec 2018yangyanli/PointCNN

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories.

3D OBJECT UNDERSTANDING INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Path Aggregation Network for Instance Segmentation

CVPR 2018 ShuLiu1993/PANet

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

Towards End-to-End Lane Detection: an Instance Segmentation Approach

15 Feb 2018MaybeShewill-CV/lanenet-lane-detection

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.

INSTANCE SEGMENTATION LANE DETECTION SEMANTIC SEGMENTATION

PixelLink: Detecting Scene Text via Instance Segmentation

4 Jan 2018ZJULearning/pixel_link

Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression plays a key role in the acquisition of bounding boxes in these methods, but it is not indispensable because text/non-text prediction can also be considered as a kind of semantic segmentation that contains full location information in itself.

INSTANCE SEGMENTATION SCENE TEXT DETECTION SEMANTIC SEGMENTATION TEXT CLASSIFICATION