YOLACT++ Better Real-Time Instance Segmentation

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

doi:10.1109/tpami.2020.3014297

Cited by 348 publications

(216 citation statements)

References 46 publications

Supporting

Mentioning

215

Contrasting

Unclassified

Order By: Relevance

“…Although the above mentioned frameworks perform better in terms of accuracy, the speed of detection remains an issue when the real time segmentation is to be performed. YOLACT (Bolya et al, 2019a) and YOLACT++ (Bolya et al, 2019b) addresses the segmentation speed at the cost of a reduction in AP by prototyping the masks and producing the instance masks with previously predicted mask coefficients. Most recent methods SOLO (Wang et al, 2020a) and SOLOv2 (Wang et al, 2020b) that addresses both speed and AP provides a simple, fast yet strong segmentation framework.…”

Section: Discussionmentioning

confidence: 99%

Instance Segmentation to Estimate Consumption of Corn Ears by Wild Animals for GMO Preference Tests

Adke

Mogel²,

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

The Genetically Modified (GMO) Corn Experiment was performed to test the hypothesis that wild animals prefer Non-GMO corn and avoid eating GMO corn, which resulted in the collection of complex image data of consumed corn ears. This study develops a deep learning-based image processing pipeline that aims to estimate the consumption of corn by identifying corn and its bare cob from these images, which will aid in testing the hypothesis in the GMO Corn Experiment. Ablation uses mask regional convolutional neural network (Mask R-CNN) for instance segmentation. Based on image data annotation, two approaches for segmentation were discussed: identifying whole corn ears and bare cob parts with and without corn kernels. The Mask R-CNN model was trained for both approaches and segmentation results were compared. Out of the two, the latter approach, i.e., without the kernel, was chosen to estimate the corn consumption because of its superior segmentation performance and estimation accuracy. Ablation experiments were performed with the latter approach to obtain the best model with the available data. The estimation results of these models were included and compared with manually labeled test data with R2 = 0.99 which showed that use of the Mask R-CNN model to estimate corn consumption provides highly accurate results, thus, allowing it to be used further on all collected data and help test the hypothesis of the GMO Corn Experiment. These approaches may also be applied to other plant phenotyping tasks (e.g., yield estimation and plant stress quantification) that require instance segmentation.

show abstract

Section: Discussionmentioning

confidence: 99%

Instance Segmentation to Estimate Consumption of Corn Ears by Wild Animals for GMO Preference Tests

Adke

Mogel²,

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…In such a situation, twostep segmentation techniques that first detect bounding boxes and then segment them should not work very well. To test this, we will consider various architectures of the common model Mask R-CNN [18] with light backbones, as well as their modern counterpart YOLACT++ [21].…”

Section: Methodology a Real-time Instance Segmentation Of Indoor Scenesmentioning

confidence: 99%

“…[20], but this negatively affects the quality of detection and segmentation. The modern development of two-stage segmentation is the relatively fast model YOLACT++ [21]. Another approach to improving the quality of segmentation of found objects involves deformation of the found contour with a special neural network, for example, based on the polar representation of the contour in PolarMask [22], the concept of the circular convolution in Deep Snake [23], or deep polygon transformer in PolyTransorfm [24].…”

Section: B Real-time Object Segmentationmentioning

confidence: 99%

Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning

et al. 2020

View full text Add to dashboard Cite

In the last years, deep learning and reinforcement learning methods have significantly improved mobile robots in such fields as perception, navigation, and planning. But there are still gaps in applying these methods to real robots due to the low computational efficiency of recent neural network architectures and their poor adaptability to robotic experiments' realities. In this paper, we consider an important task in mobile robotics -navigation to an object using an RGB-D camera. We develop a new neural network framework for robot control that is fast and resistant to possible noise in sensors and actuators. We propose an original integration of semantic segmentation, mapping, localization, and reinforcement learning methods to improve the effectiveness of exploring the environment, finding the desired object, and quickly navigating to it. We created a new HISNav dataset based on the Habitat virtual environment, which allowed us to use simulation experiments to pre-train the model and then upload it to a real robot. Our architecture is adapted to work in a real-time environment and fully implements modern trends in this area.

show abstract

“…Recently, one-stage instance segmentation methods, that do not have different branches for performing different functions, have gained more attention from researchers than two-stage methods, e.g., PolarMask [19], RDSNet [20] and YOLACT++ [21]. A two-stage method performs object detection first, then constructs a mask branch to predict each mask in a bounding box.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of deep learning algorithms for semantic segmentation of car parts

Pasupa

Kittiworapanya

Hongngern

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Evaluation of car damages from an accident is one of the most important processes in the car insurance business. Currently, it still needs a manual examination of every basic part. It is expected that a smart device will be able to do this evaluation more efficiently in the future. In this study, we evaluated and compared five deep learning algorithms for semantic segmentation of car parts. The baseline reference algorithm was Mask R-CNN, and the other algorithms were HTC, CBNet, PANet, and GCNet. Runs of instance segmentation were conducted with those five algorithms. HTC with ResNet-50 was the best algorithm for instance segmentation on various kinds of cars such as sedans, trucks, and SUVs. It achieved a mean average precision at 55.2 on our original data set, that assigned different labels to the left and right sides and 59.1 when a single label was assigned to both sides. In addition, the models from every algorithm were tested for robustness, by running them on images of parts, in a real environment with various weather conditions, including snow, frost, fog and various lighting conditions. GCNet was the most robust; it achieved a mean performance under corruption, mPC = 35.2, and a relative degradation of performance on corrupted data, compared to clean data (rPC), of 64.4%, when left and right sides were assigned different labels, and mPC = 38.1 and rPC = $$69.6\%$$ 69.6 % when left- and right-side parts were considered the same part. The findings from this study may directly benefit developers of automated car damage evaluation system in their quest for the best design.

show abstract

YOLACT++ Better Real-Time Instance Segmentation

Cited by 348 publications

References 46 publications

Instance Segmentation to Estimate Consumption of Corn Ears by Wild Animals for GMO Preference Tests

Instance Segmentation to Estimate Consumption of Corn Ears by Wild Animals for GMO Preference Tests

Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning

Evaluation of deep learning algorithms for semantic segmentation of car parts

Contact Info

Product

Resources

About