ISDA: Position-Aware Instance Segmentation with Deformable Attention

2022-02-23 · Kaining Ying, Zhenhua Wang, Cong Bai, Pengfei Zhou

Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end instance segmentation method termed ISDA. It reshapes the task into predicting a set of object masks, which are generated via traditional convolution operation with learned position-aware kernels and features of objects. Such kernels and features are learned by leveraging a deformable attention network with multi-scale representation. Thanks to the introduced set-prediction mechanism, the proposed method is NMS-free. Empirically, ISDA outperforms Mask R-CNN (the strong baseline) by 2.6 points on MS-COCO, and achieves leading performance compared with recent models. Code will be available soon.

📄 PDF Abstract BibTeX arXiv:2202.12251

Code (1)

yingkaining/isda 공식 구현 pytorch

Tasks

Instance SegmentationPositionSegmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

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…

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 $x$…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

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…

Mask R-CNN Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an…

DeVIS: Making Deformable Transformers Work for Video Instance Segmentation

2022-07-22 · Adrià Caelles, Tim Meinhardt, Guillem Brasó, Laura Leal-Taixé

Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design…

Instance Segmentation object-detection Object Detection Segmentation+2

Deformable Mamba for Wide Field of View Segmentation

2024-11-25 · Jie Hu, Junwei Zheng, Jiale Wei, Jiaming Zhang 외

Wide-FoV cameras, like fisheye and panoramic setups, are essential for broader perception but introduce significant distortions in 180{\deg} and 360{\deg} images, complicating dense prediction tasks. For instance, existi…

Decoder Mamba Segmentation Semantic Segmentation

Towards Instance Segmentation with Polygon Detection Transformers

2026-03-10 · Jiacheng Sun, Jiaqi Lin, Wenlong Hu, Haoyang Li 외 arxiv

One of the bottlenecks for instance segmentation today lies in the conflicting requirements of high-resolution inputs and lightweight, real-time inference. To address this bottleneck, we present a Polygon Detection Trans…

Instance Segmentation Cell Segmentation

Instance Search via Instance Level Segmentation and Feature Representation

2018-06-10 · Yu Zhan, Wan-Lei Zhao

Instance search is an interesting task as well as a challenging issue due to the lack of effective feature representation. In this paper, an instance level feature representation built upon fully convolutional instance-a…

Instance Search Instance Segmentation Segmentation Semantic Segmentation

CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection

2020-03-20 · CVPR 2020 6 · Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang 외

Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which…

Instance Segmentation object-detection Object Detection Position+2