On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption
| Autor: | Charles Lehman, Ghassan AlRegib, Dogancan Temel |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Entropy (classical thermodynamics) Robustness (computer science) 0502 economics and business FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Entropy (information theory) Segmentation Entropy (energy dispersal) 050210 logistics & transportation business.industry Entropy (statistical thermodynamics) Image and Video Processing (eess.IV) 05 social sciences Pattern recognition Sigmoid function Electrical Engineering and Systems Science - Image and Video Processing Softmax function Task analysis 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | ICIP |
| Popis: | Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robustness to out-of-distribution inputs for semantic segmentation models for little to no cost. In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid in order to improve understanding their relationship to robustness. As a result of this analysis, we propose combining Sigmoid with IBE (SCrIBE) to improve robustness. Finally, we demonstrate that SCrIBE exhibits superior segmentation performance aggregated across all corruptions and severity levels with a mIOU of 42.1 compared to both IBE 40.3 and the Softmax Baseline 37.5. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|