Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking
Siamese network has been a de facto benchmark framework for 3D LiDAR object tracking with a shared-parametric encoder extracting features from template and search region, respectively. This paradigm relies heavily on an additional matching network to model the cross-correlation/similarity of the template and search region. In this paper, we forsake the conventional Siamese paradigm and propose a novel single-branch framework, SyncTrack, synchronizing the feature extracting and matching to avoid forwarding encoder twice for template and search region as well as introducing extra parameters of matching network. The synchronization mechanism is based on the dynamic affinity of the Transformer, and an in-depth analysis of the relevance is provided theoretically. Moreover, based on the synchronization, we introduce a novel Attentive Points-Sampling strategy into the Transformer layers (APST), replacing the random/Farthest Points Sampling (FPS) method with sampling under the supervision of attentive relations between the template and search region. It implies connecting point-wise sampling with the feature learning, beneficial to aggregating more distinctive and geometric features for tracking with sparse points. Extensive experiments on two benchmark datasets (KITTI and NuScenes) show that SyncTrack achieves state-of-the-art performance in real-time tracking.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object TrackingObject TrackingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CASSPR: Cross Attention Single Scan Place Recognition
Place recognition based on point clouds (LiDAR) is an important component for autonomous robots or self-driving vehicles. Current SOTA performance is achieved on accumulated LiDAR submaps using either point-based or voxe…
Single-branch Network for Multimodal Training
With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text. Researchers have focused on building autonomous systems capable of processing such multi…
Cross-Modal RetrievalRetrievalAdaptive Cross-Domain Learning for Generalizable Person Re-Identification
Domain Generalizable Person Re-Identification (DG-ReID) is a more practical ReID task that is trained from multiple source domains and tested on the unseen target domains. Most existing methods are challenged for dealing…
Generalizable Person Re-identificationPerson Re-IdentificationUnsupervised Domain AdaptationHybrid Deep Learning for Traceability and Classification of Industrial Slate Tiles
Applying deep learning to instance-aware reidentification of slate tiles and extraction site classification can improve production efficiency and quality control in the slate tile industry. These tasks are particularly i…
Image MatchingOn the Branching Bias of Syntax Extracted from Pre-trained Language Models
Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branchin…