Paper Overview
Field: Computer Vision (CV) Authors: Jianjian Yin, Tao Chen, Yi Chen Released: 2025-03-18 arXiv: 2503.13840
Summary
Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial structure of spatial and class aggregations, leading to knowledge interference between class-level semantics and spatial context.
To address this, the paper proposes PCA-Seg, a simple yet effective parallel cost aggregation paradigm that enables the model to capture richer vision-language alignment information from cost volumes.
Key Contributions
1. Expert-driven perceptual learning (EPL) module: Efficiently integrates semantic and contextual streams. It incorporates a multi-expert parser to extract complementary features from multiple perspectives, and a coefficient mapper that adaptively learns pixel-specific weights for each feature, integrating complementary knowledge into a unified and robust feature embedding.
2. Feature orthogonalization decoupling (FOD) strategy: Mitigates redundancy between the semantic and contextual streams, allowing the EPL module to learn diverse knowledge from orthogonalized features.
Results
Extensive experiments on eight benchmarks demonstrate that each parallel block in PCA-Seg adds only 0.35M parameters while achieving state-of-the-art OSPS performance.
--- *Auto-collected on 2026-03-19*