Domain Adaptive Semantic Segmentation of Remote Sensing Images via Self-Training-Based Dual-Level Data Augmentation

Engineering

• Input Level 100%
• Domain Feature 66%
• Experimental Result 33%
• State-of-the-Art Method 33%
• Sensing Imagery 33%
• Adaptability 33%
• Feature Space 33%
• Level Feature 33%
• Recognition Model 33%
• Performance Degradation 33%
• Prediction Network 33%
• Perturbation Technique 33%
• Mixing Strategy 33%

Computer Science

• Image Segmentation 100%
• Remote Sensing Image 100%
• Data Augmentation 100%
• Segmentation Model 28%
• Domain Feature 28%
• Semantic Feature 14%
• Experimental Result 14%
• remote sensing imagery 14%
• Feature Space 14%
• Performance Degradation 14%
• Invariant Domain 14%
• Applied Technique 14%
• Class Imbalance 14%