ALBA : Reinforcement Learning for Video Object Segmentation

05/26/2020
by   Shreyank N Gowda, et al.
42

We consider the challenging problem of zero-shot video object segmentation (VOS). That is, segmenting and tracking multiple moving objects within a video fully automatically, without any manual initialization. We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time. We propose a network architecture for tractably performing proposal selection and joint grouping. Crucially, we then show how to train this network with reinforcement learning so that it learns to perform the optimal non-myopic sequence of grouping decisions to segment the whole video. Unlike standard supervised techniques, this also enables us to directly optimize for the non-differentiable overlap-based metrics used to evaluate VOS. We show that the proposed method, which we call ALBA outperforms the previous stateof-the-art on three benchmarks: DAVIS 2017 [2], FBMS [20] and Youtube-VOS [27].

READ FULL TEXT

page 1

page 5

page 8

page 9

research
03/13/2019

RVOS: End-to-End Recurrent Network for Video Object Segmentation

Multiple object video object segmentation is a challenging task, special...
research
07/03/2023

Segment Anything Meets Point Tracking

The Segment Anything Model (SAM) has established itself as a powerful ze...
research
05/20/2018

Unsupervised Video Object Segmentation for Deep Reinforcement Learning

We present a new technique for deep reinforcement learning that automati...
research
09/30/2019

Towards Good Practices for Video Object Segmentation

Semi-supervised video object segmentation is an interesting yet challeng...
research
12/05/2019

3D Objectness Estimation via Bottom-up Regret Grouping

3D objectness estimation, namely discovering semantic objects from 3D sc...
research
03/02/2015

Grouping and Recognition of Dot Patterns with Straight Offset Polygons

When the boundary of a familiar object is shown by a series of isolated ...
research
12/30/2015

Actor-Action Semantic Segmentation with Grouping Process Models

Actor-action semantic segmentation made an important step toward advance...

Please sign up or login with your details

Forgot password? Click here to reset