The reviewed record of science sign in
Pith

arxiv: 2411.02858 · v1 · pith:F2H6KLY7 · submitted 2024-11-05 · cs.CV

OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing

Reviewed by Pithpith:F2H6KLY7open to challenge →

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

Multi-object multi-part scene segmentation is a challenging task whose complexity scales exponentially with part granularity and number of scene objects. To address the task, we propose a plug-and-play approach termed OLAF. First, we augment the input (RGB) with channels containing object-based structural cues (fg/bg mask, boundary edge mask). We propose a weight adaptation technique which enables regular (RGB) pre-trained models to process the augmented (5-channel) input in a stable manner during optimization. In addition, we introduce an encoder module termed LDF to provide low-level dense feature guidance. This assists segmentation, particularly for smaller parts. OLAF enables significant mIoU gains of $\mathbf{3.3}$ (Pascal-Parts-58), $\mathbf{3.5}$ (Pascal-Parts-108) over the SOTA model. On the most challenging variant (Pascal-Parts-201), the gain is $\mathbf{4.0}$. Experimentally, we show that OLAF's broad applicability enables gains across multiple architectures (CNN, U-Net, Transformer) and datasets. The code is available at olafseg.github.io

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.