Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Chanyoung, Ju, Dayun, Han, Woojung, Yang, Ming-Hsuan, Hwang, Seong Jae
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909567911198720
author Kim, Chanyoung
Ju, Dayun
Han, Woojung
Yang, Ming-Hsuan
Hwang, Seong Jae
author_facet Kim, Chanyoung
Ju, Dayun
Han, Woojung
Yang, Ming-Hsuan
Hwang, Seong Jae
contents Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning schemes. Notably, training-free methods offer scalable, easily deployable solutions for handling unseen data, a key goal of OVSS. Yet, a critical issue persists: lack of object-level context consideration when segmenting complex objects in the challenging environment of OVSS based on arbitrary query prompts. This oversight limits models' ability to group semantically consistent elements within object and map them precisely to user-defined arbitrary classes. In this work, we introduce a novel approach that overcomes this limitation by incorporating object-level contextual knowledge within images. Specifically, our model enhances intra-object consistency by distilling spectral-driven features from vision foundation models into the attention mechanism of the visual encoder, enabling semantically coherent components to form a single object mask. Additionally, we refine the text embeddings with zero-shot object presence likelihood to ensure accurate alignment with the specific objects represented in the images. By leveraging object-level contextual knowledge, our proposed approach achieves state-of-the-art performance with strong generalizability across diverse datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17150
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
Kim, Chanyoung
Ju, Dayun
Han, Woojung
Yang, Ming-Hsuan
Hwang, Seong Jae
Computer Vision and Pattern Recognition
Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning schemes. Notably, training-free methods offer scalable, easily deployable solutions for handling unseen data, a key goal of OVSS. Yet, a critical issue persists: lack of object-level context consideration when segmenting complex objects in the challenging environment of OVSS based on arbitrary query prompts. This oversight limits models' ability to group semantically consistent elements within object and map them precisely to user-defined arbitrary classes. In this work, we introduce a novel approach that overcomes this limitation by incorporating object-level contextual knowledge within images. Specifically, our model enhances intra-object consistency by distilling spectral-driven features from vision foundation models into the attention mechanism of the visual encoder, enabling semantically coherent components to form a single object mask. Additionally, we refine the text embeddings with zero-shot object presence likelihood to ensure accurate alignment with the specific objects represented in the images. By leveraging object-level contextual knowledge, our proposed approach achieves state-of-the-art performance with strong generalizability across diverse datasets.
title Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17150