Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning
Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments during inference under continuous domain shifts. Most existing CTTA-OD methods prioritize effectiveness while overlooking computational efficiency, which is crucial for resource-constrained scenarios. In this paper, we propose an efficient CTTA-OD method via pruning. Our motivation stems from the observation that not all learned source features are beneficial; certain domain-sensitive feature channels can adversely affect target domain performance. Inspired by this, we introduce a sensitivity-guided channel pruning strategy that quantifies each channel based on its sensitivity to domain discrepancies at both image and instance levels. We apply weighted sparsity regularization to selectively suppress and prune these sensitive channels, focusing adaptation efforts on invariant ones. Additionally, we introduce a stochastic channel reactivation mechanism to restore pruned channels, enabling recovery of potentially useful features and mitigating the risks of early pruning. Extensive experiments on three benchmarks show that our method achieves superior adaptation performance while reducing computational overhead by 12% in FLOPs compared to the recent SOTA method.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational Efficiencyobject-detectionObject DetectionSensitivityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, targ…
Domain AdaptationObjectobject-detectionObject Detection+1MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection
Enhancing the accuracy and efficiency of machine learning algorithms employed in neural interface systems is crucial for advancing next-generation intelligent therapeutic devices. However, current systems often utilize b…
Additive modelsEEGSeizure DetectionSensitivity+1FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection
Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attributes (e.g., brightness, texture) and object categories. Existing test-t…
Test-time AdaptationObject DetectionReward-Guided Semantic Evolution for Test-time Adaptive Object Detection
Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text emb…
Object DetectionGaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing
This work introduces a new preprocessing step for object detection applicable to UAV bird's eye view imagery, which we call Adaptive Resizing. By design, it helps alleviate the challenges coming with the vast variances i…
GPUobject-detectionObject Detection