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

arXiv: https://arxiv.org/abs/2609.08011 · HTML: https://mlsanity.com/paper/2609.08011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss](https://mlsanity.com/paper/2404.01692/) (2024)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [Exploiting Diffusion Prior for Task-driven Image Restoration](https://mlsanity.com/paper/2507.22459/) (2025)
- [TaskTok: Delving into Task Tokens for Task-driven Image Restoration](https://mlsanity.com/paper/2606.26615/) (2026)

## Abstract (arXiv)

Image restoration is commonly applied before object detection under adverse conditions, yet a visually improved image need not improve the downstream task. We study this mismatch as restoration utility prediction: given a degraded image and its candidate restoration, should the restoration be used or should the original observation be preserved? We introduce TaskGuard, a post-hoc controller for frozen restoration and detection pipelines. TaskGuard characterizes the realized restoration residual through its interaction with detector sensitivity and predicts whether the intervention is task-beneficial. Exact regional counterfactuals reveal substantial within-image utility heterogeneity, while a deployable pseudo-gradient preserves statistically reliable directional information. Feature-group ablation further shows that task-conditioned evidence contributes information beyond detector-response and residual statistics. The TaskGuard utility predictor is trained only on Gaussian degradation and frozen before final evaluation, then transferred to unseen motion blur, rain, and defocus. Across these unseen families, TaskGuard reduces lossnegative interventions by 54.2% (family macro) and practical per-image detection deteriorations by 37.0% (pooled), while preserving 98.8% of the Always-Restore COCO AP. On natural-rain DAWN, it reduces loss-negative interventions by 97.9% while retaining 77.8% of the AP improvement obtained by deraining. These results support restoration utility as a task-conditioned property of the specific intervention rather than image appearance alone.