CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
CPSeg : Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting. / Li, Lei.
2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2024. s. 502-511.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - CPSeg
T2 - WACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision
AU - Li, Lei
PY - 2024
Y1 - 2024
N2 - Natural scene analysis and remote sensing imagery offer immense potential for advancements in large-scale language-guided context-aware data utilization. This potential is particularly significant for enhancing performance in downstream tasks such as object detection and segmentation with designed language prompting. In light of this, we introduce the CPSeg (Chain-of-Thought Language Prompting for Finer-grained Semantic Segmentation), an innovative framework designed to augment image segmentation performance by integrating a novel "Chain-of-Thought" process that harnesses textual information associated with images. This groundbreaking approach has been applied to a flood disaster scenario. CPSeg encodes prompt texts derived from various sentences to formulate a coherent chain-of-thought. We use a new vision-language dataset, FloodPrompt, which includes images, semantic masks, and corresponding text information. This not only strengthens the semantic understanding of the scenario but also aids in the key task of semantic segmentation through an interplay of pixel and text matching maps. Our qualitative and quantitative analyses validate the effectiveness of CPSeg.
AB - Natural scene analysis and remote sensing imagery offer immense potential for advancements in large-scale language-guided context-aware data utilization. This potential is particularly significant for enhancing performance in downstream tasks such as object detection and segmentation with designed language prompting. In light of this, we introduce the CPSeg (Chain-of-Thought Language Prompting for Finer-grained Semantic Segmentation), an innovative framework designed to augment image segmentation performance by integrating a novel "Chain-of-Thought" process that harnesses textual information associated with images. This groundbreaking approach has been applied to a flood disaster scenario. CPSeg encodes prompt texts derived from various sentences to formulate a coherent chain-of-thought. We use a new vision-language dataset, FloodPrompt, which includes images, semantic masks, and corresponding text information. This not only strengthens the semantic understanding of the scenario but also aids in the key task of semantic segmentation through an interplay of pixel and text matching maps. Our qualitative and quantitative analyses validate the effectiveness of CPSeg.
U2 - 10.1109/WACV57701.2024.00057
DO - 10.1109/WACV57701.2024.00057
M3 - Article in proceedings
SP - 502
EP - 511
BT - 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
PB - IEEE
Y2 - 4 January 2024 through 8 January 2024
ER -
ID: 378943255