Mask Propagation Network for Video Object Segmentation

2018-10-24 · Jia Sun, Dongdong Yu, Yinghong Li, Changhu Wang

In this work, we propose a mask propagation network to treat the video segmentation problem as a concept of the guided instance segmentation. Similar to most MaskTrack based video segmentation methods, our method takes the mask probability map of previous frame and the appearance of current frame as inputs, and predicts the mask probability map for the current frame. Specifically, we adopt the Xception backbone based DeepLab v3+ model as the probability map predictor in our prediction pipeline. Besides, instead of the full image and the original mask probability, our network takes the region of interest of the instance, and the new mask probability which warped by the optical flow between the previous and current frames as the inputs. We also ensemble the modified One-Shot Video Segmentation Network to make the final predictions in order to retrieve and segment the missing instance.

📄 PDF Abstract BibTeX arXiv:1810.10289

Code (0)

등록된 구현이 없습니다.

Tasks

Instance SegmentationObjectOptical Flow Estimation Segmentation Semantic Segmentation Video Object Segmentation Video Segmentation Video Semantic Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Dilated Convolution 설명 없음

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

DeepLab 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Segment Anything Meets Point Tracking

2023-07-03 · Frano Rajič, Lei Ke, Yu-Wing Tai, Chi-Keung Tang 외

The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both…

Interactive Video Object Segmentation Object Point Tracking Segmentation+4

Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation

2019-12-10 · CVPR 2020 6 · Gedas Bertasius, Lorenzo Torresani

We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence. Our method, named MaskProp, adapts the popular Mask R-CNN to video by adding a mask propagation branch t…

Instance Segmentation Object Segmentation Semantic Segmentation+1

Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation

2025-03-05 · Suhwan Cho, Seunghoon Lee, Minhyeok Lee, Jungho Lee 외

Referring video object segmentation aims to segment and track a target object in a video using a natural language prompt. Existing methods typically fuse visual and textual features in a highly entangled manner, processi…

Object Referring Video Object Segmentation Segmentation Semantic Segmentation+2

Mask Selection and Propagation for Unsupervised Video Object Segmentation

2021-01-05 · Shubhika Garg, Vidit Goel

In this work we present a novel approach for Unsupervised Video Object Segmentation, that is automatically generating instance level segmentation masks for salient objects and tracking them in a video. We efficiently han…

Segmentation Semantic Segmentation Unsupervised Video Object Segmentation Video Object Segmentation+1

Revisiting Click-based Interactive Video Object Segmentation

2022-03-03 · Stephane Vujasinovic, Sebastian Bullinger, Stefan Becker, Norbert Scherer-Negenborn 외

While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Video Object Segmentation (CiVOS) framewor…

Interactive Video Object Segmentation Object Segmentation Semantic Segmentation+2