Task-Sensitive Geometry of Representation Transfer for Object Detection under Image Degradation

Van Vung Pham

cs.CVOct 3, 2026

Task-Sensitive Geometry of Representation Transfer for Object Detection under Image Degradation

Authors: Van Vung Pham

Organizations: Computer Science Department, Sam Houston State University, Huntsville, Texas, USA

Abstract

Object detection under image degradation can benefit from clean-image supervision, but aggregate gains do not imply that transferred representation changes are uniformly useful. We study how clean task knowledge affects degraded-image representations and whether local responses to structured representation directions can be characterized geometrically. Using paired clean and Gaussian-degraded BDD100K images, we show that clean-teacher distillation improves observed detection accuracy while producing heterogeneous object-level transfer. We isolate a representation component complementary to direct clean-teacher alignment and map it into the distilled student space through an orthogonal bridge. Controlled interventions rescue 13.22% of objects lost under the distilled representation, versus 4.30% under norm-matched random perturbations, with very low harm on preserved objects. We introduce task-sensitive geometry, a gradient-derived channel-space geometry constructed from normalized detection-loss gradients. On a reserved cohort, mapped-complement orientation within this frozen geometry is positively associated with local intervention-response magnitude after controlling for intervention magnitude (partial Spearman $ρ$ = 0.242, 95% CI [0.108, 0.359]). The relationship eplicates on independent data ( $ρ$ = 0.180) and with RT-DETR-L ( $ρ$ = 0.227), but not for the direct clean-teacher residual family, and it weakens for large interventions. Routing rules and specialized distillation objectives based on these signals do not yield statistically reliable gains over CLEANKD. These results support a local, direction-family-dependent task-sensitive geometry while showing that converting such structure into improved global training remains an open problem.

Figures & tables

Panel of Figure 1 — Figure 1: Overview of the proposed framework. Paired clean and degraded observations establish clean-to-degraded representation transfer through CLEAN-KD. Object-level analysis reveals heterogeneous transfer outcomes, while complementary representation interventions identify task-relevant information beyond direct clean-teacher alignment. Task-sensitive geometry characterizes candidate representation directions using downstream task gradients and is evaluated prospectively against measured intervention responses.

Panel of Figure 2 — Figure 2: Conceptual illustration of task-sensitive representation geometry. Normalized downstream task gradients define recurrent task-sensitive orientations in feature-channel space. Candidate directions of comparable magnitude can therefore have different orientation scores. A direction such as $d_{\mathrm{high}}$ , which is more strongly aligned with the dominant task-sensitive orientation, yields a larger $q(d)$ than a direction such as $d_{\mathrm{low}}$ . The illustration is schematic and does not represent an empirical two-dimensional projection of $C_{g}$ .

Figure 3: Detection performance of degraded-only training (NONE) and clean-teacher distillation (CLEAN-KD) across the evaluated settings. CLEAN-KD produces positive observed mAP 50:95 differences on YOLO11s Gaussian development, Gaussian DEVTEST, ACDC, and RT-DETR-L Gaussian validation. DEVTEST and ACDC are descriptive point estimates because paired confidence intervals were not computed for these evaluations. For RT-DETR-L, the macro difference is positive, but its paired 95% confidence interval includes zero.

Figure 4: Qualitative examples of mapped-complement rescue under Gaussian image degradation. Each row shows a frozen validation case in which the target object is detected by the degraded-only NONE model, lost under CLEAN-KD, and recovered after injecting the basis-mapped complementary representation into the frozen CLEAN-KD feature map. One confirmed mapped-complement rescue is selected at each Gaussian degradation severity $\sigma=15$ , $25$ , and $50$ using a deterministic fixed-seed procedure (seed 2027) from the 129 targeted rescues, with distinct source images. Selection does not condition on post-intervention confidence, IoU, or the matched-random control outcome. Red dashed boxes indicate the target ground-truth object, and green boxes indicate the matched target prediction when present. Non-target detections are suppressed for visual clarity. These examples illustrate the object-level intervention mechanism and do not represent a separately trained detector or a TSG-guided inference method.

Figure 5: Summary of the principal task-sensitive-geometry validation results. The prospective mapped-complement analysis shows a positive partial association between task-sensitive orientation and local intervention response after controlling for intervention magnitude. The relationship replicates on an independent fresh cohort and under RT-DETR-L. In contrast, the corresponding analysis for the direct clean-teacher residual does not support direction-family generalization. The locality analysis further shows a stronger orientation–response association for the local intervention regime than for the substantially larger intervention step. Points denote observed correlation estimates or, for the locality analysis, the difference in correlations; horizontal bars denote source-bootstrap 95% confidence intervals.

Method	Architecture	Macro mAP 50:95	Main conclusion
CLEAN-KD	YOLO11s	0.207666	Reference method
BOUNDARY-KD	YOLO11s	0.205126	Lower macro point estimate
PS-CLEAN-KD (exact-box)	YOLO11s	0.205226	Lower macro point estimate
COMP-KD	YOLO11s	0.207522	No reliable improvement
GCOMP-KD (R2)	YOLO11s	0.210226	No reliable improvement established
GCOMP-KD (R0)	YOLO11s	0.211951	R0–R2 CI includes zero

Table 1: Summary of specialized transfer objectives. For GCOMP-KD, R0 denotes undilated exact-box P4 support and R2 denotes the same support square-dilated by two P4 cells. Results are not interpreted as a common ranking because several variants address different hypotheses and, where noted, lack a paired confidence interval against CLEAN-KD.

Object Detection

Object detection locates and classifies objects in images or video, balancing localization accuracy, robustness, and inference speed.

See all 624 papers

Self-Aware Object Detection via Degradation Manifolds
Feb 20, 2026Stefan Becker, Simon Weiss, Wolfgang Hübner +1Object Detection OOD Detection
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB Gutleuthausstraße 1, 76275 Ettlingen
Distilling Vision Transformers for Distortion-Robust Representation Learning
Apr 24, 2026Konstantinos Alexis, Giorgos Giannopoulos, Dimitrios GunopulosRepresentation Learning Visual Representation Learning
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Greece · National Observatory of Athens, Greece
TaskGuard: Task-Conditioned Restoration Utility for Risk-Aware Object Detection
Sep 7, 2026Vung PhamImage Corruption Robustness Image Restoration
Computer Science Department, Sam Houston State University, Huntsville, Texas, USA

Feb 20, 2026J/K move · Enter open · S save

Self-Aware Object Detection via Degradation Manifolds

Stefan Becker, Simon Weiss, Wolfgang Hübner, Michael Arens

Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB Gutleuthausstraße 1, 76275 Ettlingen

Object Detection OOD Detection

Open paper AskPDF arXiv

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.

Abstract

Object Detection

Explore similar work

Self-Aware Object Detection via Degradation Manifolds

Distilling Vision Transformers for Distortion-Robust Representation Learning

TaskGuard: Task-Conditioned Restoration Utility for Risk-Aware Object Detection