FourierNet: Compact Mask Representation for Instance Segmentation Using Differentiable Shape Decoders

  title={FourierNet: Compact Mask Representation for Instance Segmentation Using Differentiable Shape Decoders},
  author={Nuri Benbarka and Hamd ul Moqeet Riaz and Andreas Zell},
  journal={2020 25th International Conference on Pattern Recognition (ICPR)},
We present FourierNet, a single shot, anchor-free, fully convolutional instance segmentation method that predicts a shape vector. Consequently, this shape vector is converted into the masks' contour points using a fast numerical transform. Compared to previous methods, we introduce a new training technique, where we utilize a differentiable shape decoder, which manages the automatic weight balancing of the shape vector's coefficients. We used the Fourier series as a shape encoder because of its… 

Figures and Tables from this paper

TextFourierNet: Arbitrary-shaped Scene Text Detection Based on Fourier Contour Modeling

A novel arbitrary-shaped scene text detector named TextFourierNet is proposed, which is a regression-based method that model arbitrary- shaped scene text instances in polar coordinates and encode the complex geometric layouts into simple Fourier coefficients.

SCR: Smooth Contour Regression with Geometric Priors

This work introduces SCR: a method that captures resolution-free object contours as complex periodic functions, and designs a compact version of the method, which is benchmarked on embedded hardware with a wide range of power targets, achieving up to real-time performance.

BézierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images

The proposed BézierSeg model is an efficient, accurate, robust and concise solution that simplifies the whole segmentation pipeline in AI-assisted applications and achieves accuracy competitive with pixel-wise segmentation models at fuzzy boundaries.

FCSN: Global Context Aware Segmentation by Learning the Fourier Coefficients of Objects in Medical Images

A Fourier Coefficient Segmentation Network (FCSN) is proposed-a novel global context-aware DNN model that segments an object by learning the complex Fourier coefficients of the object's masks by integrating over the whole contour.

FourierMask: Instance Segmentation using Fourier Mapping in Implicit Neural Networks

FourierMask, which employs Fourier series combined with implicit neural representations to generate instance segmentation masks, shows competitive results on the MS COCO dataset compared to the baseline Mask R-CNN at the same output resolution and surpasses it on higher resolution.

YOLACT++ Better Real-Time Instance Segmentation

A simple, fully-convolutional model for real-time instance segmentation that achieves competitive results on MS COCO evaluated on a single Titan Xp, which is significantly faster than any previous state-of-the-art approach.

INSTA-YOLO: Real-Time Instance Segmentation

This paper proposes Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation that predicts instances as object contours represented by 2D points in Cartesian space.

Comparative Study of Movie Shot Classification Based on Semantic Segmentation

The performance of shot type classification was improved by preprocessing the semantic segmentation of the frame extracted from the movie by comparing and evaluating performance using ResNet-50 and Yolact as pretreatments forshot type classification.



PolarMask: Single Shot Instance Segmentation With Polar Representation

  • Enze XiePei Sun Ping Luo
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most

YOLACT: Real-Time Instance Segmentation

We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any

Explicit Shape Encoding for Real-Time Instance Segmentation

In this paper, we propose a novel top-down instance segmentation framework based on explicit shape encoding, named \textbf{ESE-Seg}. It largely reduces the computational consumption of the instance

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

ShapeMask is introduced, which learns the intermediate concept of object shape to address the problem of generalization in instance segmentation to novel categories and significantly outperforms the state-of-the-art when learning across categories.

CenterMask: Real-Time Anchor-Free Instance Segmentation

We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector

PolyTransform: Deep Polygon Transformer for Instance Segmentation

In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and

Aggregated Residual Transformations for Deep Neural Networks

On the ImageNet-1K dataset, it is empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy and is more effective than going deeper or wider when the authors increase the capacity.

UnitBox: An Advanced Object Detection Network

A novel Intersection over Union (IoU) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit, and introduces the UnitBox, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast.

EmbedMask: Embedding Coupling for One-stage Instance Segmentation

The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.

FCOS: Fully Convolutional One-Stage Object Detection

For the first time, a much simpler and flexible detection framework achieving improved detection accuracy is demonstrated, and it is hoped that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks.