CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection

• URL: http://arxiv.org/abs/2505.23317v1
• Date: Thu, 29 May 2025 10:23:37 GMT
• Title: CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection
• Abstract summary: CF-DETR is an integrated system featuring a novel coarse-to-fine Transformer architecture and a dedicated real-time scheduling framework NPFP**.<n>It partitions each DETR task into a safety-critical coarse subtask for guaranteed critical object detection within its deadline, and an optional fine subtask for enhanced overall accuracy (R2)<n>Under an NPFP** policy, CF-DETR successfully meets strict timing guarantees for critical operations and achieves significantly higher overall and critical object detection accuracy compared to existing baselines across diverse AV workloads.
• Score: 3.002784388635573
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrently executing multiple DETR tasks presents significant challenges in meeting firm real-time deadlines (R1) and high accuracy requirements (R2), particularly for safety-critical objects, while navigating the inherent latency-accuracy trade-off under resource constraints. Existing real-time DNN scheduling approaches often treat models generically, failing to leverage Transformer-specific properties for efficient resource allocation. To address these challenges, we propose CF-DETR, an integrated system featuring a novel coarse-to-fine Transformer architecture and a dedicated real-time scheduling framework NPFP**. CF-DETR employs three key strategies (A1: coarse-to-fine inference, A2: selective fine inference, A3: multi-level batch inference) that exploit Transformer properties to dynamically adjust patch granularity and attention scope based on object criticality, aiming to satisfy R2. The NPFP** scheduling framework (A4) orchestrates these adaptive mechanisms A1-A3. It partitions each DETR task into a safety-critical coarse subtask for guaranteed critical object detection within its deadline (ensuring R1), and an optional fine subtask for enhanced overall accuracy (R2), while managing individual and batched execution. Our extensive evaluations on server, GPU-enabled embedded platforms, and actual AV platforms demonstrate that CF-DETR, under an NPFP** policy, successfully meets strict timing guarantees for critical operations and achieves significantly higher overall and critical object detection accuracy compared to existing baselines across diverse AV workloads.

Related papers

• Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models [41.32939197803798]
  Q-Zoom is a query-aware adaptive high-resolution perception framework.<n>A lightweight Gating Network safely bypasses high-resolution processing when coarse global features suffice.<n>A Self-Distilled Region Network precisely localizes the task-relevant Region-of-Interest from intermediate feature spaces.
  arXiv  Detail & Related papers  (2026-04-08T10:12:30Z)
• RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer [71.59462491691819]
  We propose a novel end-to-end differential transformer network, termed RegFormer++, for large-scale point cloud alignment.<n>Because we fill original 3D coordinates into 2D projected positions, our designed transformer can benefit from both high efficiency in 2D processing and accuracy from 3D geometric information.<n>Experiments on KITTI, NuScenes, and Argoverse datasets demonstrate that our model achieves state-of-the-art performance in terms of both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-03-15T09:03:10Z)
• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering [62.63376387138257]
  We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
  arXiv  Detail & Related papers  (2026-01-14T08:04:33Z)
• FAIM: Frequency-Aware Interactive Mamba for Time Series Classification [87.84511960413715]
  Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition.<n>We propose FAIM, a lightweight Frequency-Aware Interactive Mamba model.<n>We show that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-11-26T08:36:33Z)
• Efficient Adaptive Transformer: An Empirical Study and Reproducible Framework [0.0]
  EAT provides an open-source benchmarking pipeline that automates data processing, timing, and ablation across GLUE tasks.<n>The main contribution is the open, end-to-end reproducible framework, complete with scripts, CSV logging, and analysis utilities.
  arXiv  Detail & Related papers  (2025-10-14T11:40:48Z)
• Source-Free Object Detection with Detection Transformer [59.33653163035064]
  Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data.<n>Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR)<n>In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs.
  arXiv  Detail & Related papers  (2025-10-13T07:35:04Z)
• MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection [11.16242420187823]
  We propose MRC-DETR, a novel and efficient detection framework for bare PCB defect inspection.<n>To enhance feature representation capability, we design a Multi-Residual Directional Coupled Block (MRDCB)<n>To reduce computational redundancy caused by inefficient cross-layer information fusion, we introduce an Adaptive Screening Pyramid Network (ASPN)
  arXiv  Detail & Related papers  (2025-07-04T08:42:38Z)
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving [62.62464518137153]
  DriveTransformer is a simplified E2E-AD framework for the ease of scaling up.<n>It is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention.<n>It achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.
  arXiv  Detail & Related papers  (2025-03-07T11:41:18Z)
• Fractional Correspondence Framework in Detection Transformer [13.388933240897492]
  The Detection Transformer (DETR) has significantly simplified the matching process in object detection tasks.<n>This algorithm facilitates optimal one-to-one matching of predicted bounding boxes to ground-truth annotations during training.<n>We propose a flexible matching strategy that captures the cost of aligning predictions with ground truths to find the most accurate correspondences.
  arXiv  Detail & Related papers  (2025-03-06T05:29:20Z)
• Distribution-Aware Continual Test-Time Adaptation for Semantic Segmentation [33.75630514826721]
  We propose a distribution-aware tuning ( DAT) method to make semantic segmentation CTTA efficient and practical in real-world applications. DAT adaptively selects and updates two small groups of trainable parameters based on data distribution during the continual adaptation process. We conduct experiments on two widely-used semantic segmentation CTTA benchmarks, achieving promising performance compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-24T10:48:20Z)
• RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration [73.69415797389195]
  We propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes.
  arXiv  Detail & Related papers  (2023-03-22T08:47:37Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence [17.854940064699985]
  We propose a transformer architecture with a mitigatory self-attention mechanism. Miti-DETR reserves the inputs of each single attention layer to the outputs of that layer so that the "non-attention" information has participated in attention propagation. Miti-DETR significantly enhances the average detection precision and convergence speed towards existing DETR-based models.
  arXiv  Detail & Related papers  (2021-12-26T03:23:59Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Higher Performance Visual Tracking with Dual-Modal Localization [106.91097443275035]
  Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. We propose a dual-modal framework for target localization, consisting of robust localization suppressingors via ONR and the accurate localization attending to the target center precisely via OFC.
  arXiv  Detail & Related papers  (2021-03-18T08:47:56Z)
• Rethinking Transformer-based Set Prediction for Object Detection [57.7208561353529]
  Experimental results show that the proposed methods not only converge much faster than the original DETR, but also significantly outperform DETR and other baselines in terms of detection accuracy.
  arXiv  Detail & Related papers  (2020-11-21T21:59:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.