A dual-axis taxonomy classifies image degradations by causal source and perceptual effect, with a severity quantification layer using standard quality metrics, demonstrated via a COCO-based object detector robustness benchmark.
Towards building self-aware object detectors via reliable uncertainty quantification and calibration,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation
A dual-axis taxonomy classifies image degradations by causal source and perceptual effect, with a severity quantification layer using standard quality metrics, demonstrated via a COCO-based object detector robustness benchmark.