Browse > Computer Vision > Instance Segmentation

Instance Segmentation

107 papers with code · Computer Vision

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

( Image credit: Weakly Supervised Panoptic Segmentation )

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.

 SOTA for Instance Segmentation on Cityscapes test (using extra training data)

HUMAN PART SEGMENTATION INSTANCE SEGMENTATION KEYPOINT DETECTION MULTI-HUMAN PARSING NUCLEAR SEGMENTATION 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.

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.

INSTANCE SEGMENTATION KEYPOINT DETECTION OBJECT DETECTION VIDEO CLASSIFICATION

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

25 Apr 2019open-mmlab/mmdetection

In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation.

INSTANCE SEGMENTATION OBJECT DETECTION OBJECT RECOGNITION

Mask Scoring R-CNN

CVPR 2019 open-mmlab/mmdetection

In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Hybrid Task Cascade for Instance Segmentation

CVPR 2019 open-mmlab/mmdetection

In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.

 SOTA for Instance Segmentation on COCO test-dev (using extra training data)

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

Deformable ConvNets v2: More Deformable, Better Results

CVPR 2019 open-mmlab/mmdetection

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

Is Sampling Heuristics Necessary in Training Deep Object Detectors?

11 Sep 2019facebookresearch/maskrcnn-benchmark

To address the imbalance between foreground and background, various heuristic methods, such as OHEM, Focal Loss, GHM, have been proposed for biased sampling or weighting when training deep object detectors.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Rethinking ImageNet Pre-training

ICCV 2019 tensorpack/tensorpack

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION