Instance Segmentation With Mask-Supervised Polygonal Boundary Transformers

2022-01-01 · CVPR 2022 1 · Justin Lazarow, Weijian Xu, Zhuowen Tu

In this paper, we present an end-to-end instance segmentation method that regresses a polygonal boundary for each object instance. This sparse, vectorized boundary representation for objects, while attractive in many downstream computer vision tasks, quickly runs into issues of parity that need to be addressed: parity in supervision and parity in performance when compared to existing pixel-based methods. This is due in part to object instances being annotated with ground-truth in the form of polygonal boundaries or segmentation masks, yet being evaluated in a convenient manner using only segmentation masks. Our method, named BoundaryFormer, is a Transformer based architecture that directly predicts polygons yet uses instance mask segmentations as the ground-truth supervision for computing the loss. We achieve this by developing an end-to-end differentiable model that solely relies on supervision within the mask space through differentiable rasterization. BoundaryFormer matches or surpasses the Mask R-CNN method in terms of instance segmentation quality on both COCO and Cityscapes while exhibiting significantly better transferability across datasets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Instance Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

BoxSnake: Polygonal Instance Segmentation with Box Supervision

2023-03-21 · ICCV 2023 1 · Rui Yang, Lin Song, Yixiao Ge, Xiu Li

Box-supervised instance segmentation has gained much attention as it requires only simple box annotations instead of costly mask or polygon annotations. However, existing box-supervised instance segmentation models mainl…

Box-supervised Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation

Real-time instance segmentation with polygons using an Intersection-over-Union loss

2023-05-09 · Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau

Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compromise. In this paper, we improve over Cen…

GPU Instance Segmentation Real-time Instance Segmentation regression+1

An Object Aware Hybrid U-Net for Breast Tumour Annotation

2022-02-22 · Suvidha Tripathi, Satish Kumar Singh

In the clinical settings, during digital examination of histopathological slides, the pathologist annotate the slides by marking the rough boundary around the suspected tumour region. The marking or annotation is general…

Deep Learning Instance Segmentation Segmentation Semantic Segmentation

PolarNeXt: Rethink Instance Segmentation with Polar Representation

2025-01-01 · CVPR 2025 1 · Jiacheng Sun, Xinghong Zhou, Yiqiang Wu, Bin Zhu 외

One of the roadblocks for instance segmentation today is heavy computational overhead and model parameters. Previous methods based on Polar Representation made the initial mark to address this challenge by formulatin…

Instance Segmentation Segmentation Semantic Segmentation

A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation

2021-08-23 · ICCV 2021 10 · Khoi Nguyen, Sinisa Todorovic

This paper addresses weakly supervised amodal instance segmentation, where the goal is to segment both visible and occluded (amodal) object parts, while training provides only ground-truth visible (modal) segmentations. …

Amodal Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation