Text

SOLO : A Simple Framework for Instance Segmentation

Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the “detect-then-segment” strategy (e.g., Mask R-CNN), or predict embedding vectors first then cluster pixels into individual instances. In this paper, we view the task of instance segmentation from a completely new perspective by introducing the notion of “instance categories”, which assigns categories to each pixel within an instance according to the instance's location. With this notion, we propose s egmenting o bjects by lo cations (SOLO), a simple, direct, and fast framework for instance segmentation with strong performance. We derive a few SOLO variants (e.g., Vanilla SOLO, Decoupled SOLO, Dynamic SOLO) following the basic principle. Our method directly maps a raw input image to the desired object categories and instance masks, eliminating the need for the grouping post-processing or the bounding box detection. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy, while being considerably simpler than the existing methods. Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation. We further demonstrate the flexibility and high-quality segmentation of SOLO by extending it to perform one-stage instance-level image matting. Code is available at: https://git.io/AdelaiDet .

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.11 Part 2 November 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 8587-8601

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

OBJECT DETECTION
INSTANCE SEGMENTATION
SEGMENTING OBJECTS BY LOCATIONS

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3111116

Pernyataan Tanggungjawab

Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li

Versi lain/terkait

Lampiran Berkas

Komentar