Personalized OVSS: Understanding Personal Concept in Open-Vocabulary Semantic Segmentation
It addresses a domain-specific problem for users needing to segment personal visual concepts in images, representing an incremental advance over existing OVSS methods.
This paper tackles the problem of open-vocabulary semantic segmentation failing to understand personal texts like 'my mug cup' by introducing a personalized OVSS task and proposing a text prompt tuning-based plug-in method with negative mask proposal and visual embedding injection, achieving superior performance on new benchmarks such as FSS$^\text{per}$, CUB$^\text{per}$, and ADE$^\text{per}$.
While open-vocabulary semantic segmentation (OVSS) can segment an image into semantic regions based on arbitrarily given text descriptions even for classes unseen during training, it fails to understand personal texts (e.g., `my mug cup') for segmenting regions of specific interest to users. This paper addresses challenges like recognizing `my mug cup' among `multiple mug cups'. To overcome this challenge, we introduce a novel task termed \textit{personalized open-vocabulary semantic segmentation} and propose a text prompt tuning-based plug-in method designed to recognize personal visual concepts using a few pairs of images and masks, while maintaining the performance of the original OVSS. Based on the observation that reducing false predictions is essential when applying text prompt tuning to this task, our proposed method employs `negative mask proposal' that captures visual concepts other than the personalized concept. We further improve the performance by enriching the representation of text prompts by injecting visual embeddings of the personal concept into them. This approach enhances personalized OVSS without compromising the original OVSS performance. We demonstrate the superiority of our method on our newly established benchmarks for this task, including FSS$^\text{per}$, CUB$^\text{per}$, and ADE$^\text{per}$.