The reviewed record of science sign in
Pith

arxiv: 2010.09140 · v2 · pith:DREBTLY3 · submitted 2020-10-18 · cs.CV

Localized Interactive Instance Segmentation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DREBTLY3record.jsonopen to challenge →

classification cs.CV
keywords objectclicksinteractivesegmentationclickinginstancelocalizationpropose
0
0 comments X
read the original abstract

In current interactive instance segmentation works, the user is granted a free hand when providing clicks to segment an object; clicks are allowed on background pixels and other object instances far from the target object. This form of interaction is highly inconsistent with the end goal of efficiently isolating objects of interest. In our work, we propose a clicking scheme wherein user interactions are restricted to the proximity of the object. In addition, we propose a novel transformation of the user-provided clicks to generate a weak localization prior on the object which is consistent with image structures such as edges, textures etc. We demonstrate the effectiveness of our proposed clicking scheme and localization strategy through detailed experimentation in which we raise state-of-the-art on several standard interactive segmentation benchmarks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Confidence Sequences for Online Statistical Model Checking of Markov Decision Processes

    cs.AI 2026-06 unverdicted novelty 6.0

    Introduces and implements confidence sequences for online statistical model checking of MDPs that require 50x fewer samples than prior state-of-the-art union-bound approaches.