LeMoRe: Learn More Details for Lightweight Semantic Segmentation
This work addresses the challenge for vision tasks requiring efficient segmentation, though it appears incremental as it builds on existing paradigms with hybrid modeling.
The paper tackles the problem of balancing efficiency and performance in lightweight semantic segmentation by introducing a method that synergizes explicit and implicit modeling, achieving effective performance-efficiency trade-offs on datasets like ADE20K, CityScapes, Pascal Context, and COCO-Stuff.
Lightweight semantic segmentation is essential for many downstream vision tasks. Unfortunately, existing methods often struggle to balance efficiency and performance due to the complexity of feature modeling. Many of these existing approaches are constrained by rigid architectures and implicit representation learning, often characterized by parameter-heavy designs and a reliance on computationally intensive Vision Transformer-based frameworks. In this work, we introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity. Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies through a nested attention mechanism. Extensive experiments on challenging datasets, including ADE20K, CityScapes, Pascal Context, and COCO-Stuff, demonstrate that LeMoRe strikes an effective balance between performance and efficiency.