Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Self-Aware Object Detection via Degradation Manifolds

About

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient to produce predictions without assessing whether the input remains within the detector's nominal operating regime. We refer to this capability as self-aware object detection. We introduce a degradation-aware self-awareness framework based on degradation manifolds, which explicitly structure a detector's feature space according to image degradation rather than semantic content. Our method augments a standard detection backbone with a lightweight embedding head trained via multi-layer contrastive learning. Images sharing the same degradation composition are pulled together, while differing degradation configurations are pushed apart, yielding a geometrically organized representation that captures degradation type and severity without requiring degradation labels or explicit density modeling. To anchor the learned geometry, we estimate a pristine prototype from clean training embeddings, defining a nominal operating point in representation space. Self-awareness emerges as geometric deviation from this reference, providing an intrinsic, image-level signal of degradation-induced shift that is independent of detection confidence. Extensive experiments on synthetic corruption benchmarks, cross-dataset zero-shot transfer, and natural weather-induced distribution shifts demonstrate strong pristine-degraded separability, consistent behavior across multiple detector architectures, and robust generalization under semantic shift. These results suggest that degradation-aware representation geometry provides a practical and detector-agnostic foundation.

Stefan Becker, Simon Weiss, Wolfgang H\"ubner, Michael Arens• 2026

Related benchmarks

TaskDatasetResultRank
Degradation-induced covariate shift detectionCOCO synthetically corrupted variants
AUROC (Severity 1)88.64
32
Pristine-Degraded SeparabilitySTF heavy snow
AUROC0.7194
2
Pristine-Degraded SeparabilitySTF Dense Fog
AUROC81.5
2
Pristine-Degraded SeparabilitySTF heavy rain
AUROC86.66
2
Pristine-Degraded SeparabilityBDD heavy rain
AUROC88.52
2
Out-of-Distribution DetectionVisDrone
AUROC (Level 1)83.66
1
Out-of-Distribution DetectionKITTI
AUROC (Level 1)94.19
1
Out-of-Distribution DetectionDETRAC
AUROC (Level 1)94.65
1
Out-of-Distribution DetectionFLIR VIS
AUROC (Level 1)82.83
1
Out-of-Distribution DetectionUAVDT
AUROC (L1)92.12
1
Showing 10 of 10 rows

Other info

Follow for update