ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts
This work addresses the problem of zero-shot segmentation for computer vision researchers, offering an incremental improvement by eliminating the need for additional encoders or retraining.
The paper tackles zero-shot semantic segmentation by proposing ZegOT, a method that matches multiple text prompts with frozen image embeddings using optimal transport, achieving state-of-the-art performance on benchmark datasets.
Recent success of large-scale Contrastive Language-Image Pre-training (CLIP) has led to great promise in zero-shot semantic segmentation by transferring image-text aligned knowledge to pixel-level classification. However, existing methods usually require an additional image encoder or retraining/tuning the CLIP module. Here, we propose a novel Zero-shot segmentation with Optimal Transport (ZegOT) method that matches multiple text prompts with frozen image embeddings through optimal transport. In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed to learn an optimal mapping between multiple text prompts and visual feature maps of the frozen image encoder hidden layers. This unique mapping method facilitates each of the multiple text prompts to effectively focus on distinct visual semantic attributes. Through extensive experiments on benchmark datasets, we show that our method achieves the state-of-the-art (SOTA) performance over existing Zero-shot Semantic Segmentation (ZS3) approaches.