YOLACT: Real-time Instance Segmentation

Bolya, Daniel; Zhou, Chong; Xiao, Fanyi; Lee, Yong Jae

doi:10.48550/arxiv.1904.02689

Cited by 21 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MaskRCNN also extends the Faster-RCNN by adding an additional module that performs segmentation. 13 This is a simple, fully-convolutional model that was designed for fast instance segmentation. The real-time performance is achieved by breaking the instance segmentation into two parallel tasks: a Prototype Generation Branch and a Mask Coefficient Branch that is combined using a linear combination of the former with the latter as coefficients to assemble the final mask.…”

Section: Mask R-cnn 89mentioning

confidence: 99%

Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray

Konya

Natarajan²,

Allouch

et al. 2021

Journal of Craniovertebral Junction and Spine

View full text Add to dashboard Cite

Purpose: This study investigated the segmentation metrics of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays to test the generalization ability and robustness which are the basis of clinical decision support algorithms. Methods: Instance segmentation networks were compared to semantic segmentation networks based on different metrics. The study cohort comprised diseased spines and postoperative images with metallic implants. Results: However, the pixel accuracies and intersection over union are similarly high for the best performing instance and semantic segmentation models; the observed vertebral recognition rates of the instance segmentation models statistically significantly outperform the semantic models' recognition rates. Conclusion: The results of the instance segmentation models on lumbar spine X-ray perform superior to semantic segmentation models in the recognition rates even by images of severe diseased spines by allowing the segmentation of overlapping vertebrae, in contrary to the semantic models where such differentiation cannot be performed due to the fused binary mask of the overlapping instances. These models can be incorporated into further clinical decision support pipelines.

show abstract

Section: Mask R-cnn 89mentioning

confidence: 99%

Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray

Konya

Natarajan²,

Allouch

et al. 2021

Journal of Craniovertebral Junction and Spine

View full text Add to dashboard Cite

show abstract

“…FCIS [21] assembles the positionsensitive score maps within the ROI to directly predict segmentation results. YOLACT [4] tries to combine the prototype masks and predicted coefficients and then crops with a segmented bounding box. PolarMask [36] introduces the polar representation to formulate pixel-wise segmentation as a distance regression problem.…”

Section: Related Workmentioning

confidence: 99%

S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation

Cheng

Yang

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Real-time understanding in video is crucial in various AI applications such as autonomous driving. This work presents a fast single-shot segmentation strategy for video scene understanding. The proposed net, called S3-Net, quickly locates and segments target sub-scenes, meanwhile extracts structured time-series semantic features as inputs to an LSTM-based spatio-temporal model. Utilizing tensorization and quantization techniques, S3-Net is intended to be lightweight for edge computing. Experiments using CityScapes, UCF11, HMDB51 and MOMENTS datasets demonstrate that the proposed S3-Net achieves an accuracy improvement of 8.1% versus the 3D-CNN based approach on UCF11, a storage reduction of 6.9× and an inference speed of 22.8 FPS on CityScapes with a GTX1080Ti GPU.

show abstract

“…These are used as supervision to train a Mask R-CNN (shown as green components in Figure 2). Depending on the application, other choices of fully supervised methods can be used instead of Mask R-CNN: if the goal is to perform instance segmentation at real-time, one can consider training a YOLACT [5], and for semantic segmentation, one can consider training a DeepLab [7] segmentation network.…”

Section: Fully Supervised Segmentation Branchmentioning

confidence: 99%

Where are the Masks: Instance Segmentation with Image-level Supervision

Laradji,

Vazquez,

Schmidt

2019

Preprint

View full text Add to dashboard Cite

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To address this limitation, we propose a novel framework that can effectively train with image-level labels, which are significantly cheaper to acquire. For instance, one can do an internet search for the term "car" and obtain many images where a car is present with minimal effort. Our framework consists of two stages: (1) train a classifier to generate pseudo masks for the objects of interest; (2) train a fully supervised Mask R-CNN on these pseudo masks. Our two main contribution are proposing a pipeline that is simple to implement and is amenable to different segmentation methods; and achieves new state-of-the-art results for this problem setup. Our results are based on evaluating our method on PASCAL VOC 2012, a standard dataset for weakly supervised methods, where we demonstrate major performance gains compared to existing methods with respect to mean average precision.

show abstract

YOLACT: Real-time Instance Segmentation

Cited by 21 publications

References 0 publications

Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray

Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray

S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation

Where are the Masks: Instance Segmentation with Image-level Supervision

Contact Info

Product

Resources

About