Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots
Open-vocabulary slots, such as file name, album name, or schedule title, significantly degrade the performance of neural-based slot filling models since these slots can take on values from a virtually unlimited set and have no semantic restriction nor a length limit. In this paper, we propose a robust adversarial model-agnostic slot filling method that explicitly decouples local semantics inherent in open-vocabulary slot words from the global context. We aim to depart entangled contextual semantics and focus more on the holistic context at the level of the whole sentence. Experiments on two public datasets show that our method consistently outperforms other methods with a statistically significant margin on all the open-vocabulary slots without deteriorating the performance of normal slots.
Code (0)
등록된 구현이 없습니다.
Tasks
Sentenceslot-fillingSlot FillingSimilar Papers 제목 키워드 기반
CogVis: Must Open-Vocabulary Change Detection Perceive the Scene Anew for Every Query?
Earth-surface monitoring requires change detection models capable of recognizing arbitrary semantic categories. Open-Vocabulary Change Detection (OVCD) addresses this need. However, existing methods often entangle tempor…
Change DetectionMonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gauss…
Scene UnderstandingQuestion AnsweringWhat You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignment. However, existing paradigms typically…
Image SegmentationSegmentationSemantic SegmentationOpen Vocabulary Scene Parsing
Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a larg…
General ClassificationScene ParsingTowards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level rec…
Online ClusteringOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSemantic Segmentation