Improving Spatial Codification in Semantic Segmentation
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem. We propose to partition the image into three regions for each object to be described: Figure, Border and Ground. This partition aims at minimizing the influence of the image context on the object description and vice versa by introducing an intermediate zone around the object contour. Furthermore, we also propose a richer visual descriptor of the object by applying a Spatial Pyramid over the Figure region. Two novel Spatial Pyramid configurations are explored: Cartesian-based and crown-based Spatial Pyramids. We test these approaches with state-of-the-art techniques and show that they improve the Figure-Ground based pooling in the Pascal VOC 2011 and 2012 semantic segmentation challenges.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Establishing Morpho-semantic Relations in FarsNet (a focus on derived nouns)
This paper aims at a morpho-semantic analysis of 2461 Persian derived nouns, documented in FarsNet addressing computational codification via formulating specific morpho-semantic relations between classes of derived nouns…
DescriptiveTime-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems
Compressive imaging using coded apertures (CA) is a powerful technique that can be used to recover depth, light fields, hyperspectral images and other quantities from a single snapshot. The performance of compressive ima…
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codification readiness of implementation-facing …
Developing a Framework for Describing Relations among Language Resources
In this paper, we study relations holding between language resources as implemented in activities concerned with their documentation. We envision the term language resources with an inclusive definition covering datase…
Progressive Prompt-Guided Cross-Modal Reasoning for Referring Image Segmentation
Referring image segmentation aims to localize and segment a target object in an image based on a free-form referring expression. The core challenge lies in effectively bridging linguistic descriptions with object-level v…
Semantic SegmentationInstance SegmentationReferring ExpressionImage Segmentation