Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation
원문 초록
In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution models by distilling knowledge from a high-resolution model. However, we face the challenge of feature size mismatch and class number mismatch when applying knowledge distillation to networks with different input resolutions. To address this issue, we propose a novel cross-domain knowledge distillation (CDKD) framework. In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions. It adopts a projector ensemble to map low-resolution features into multiple common spaces and adaptively merges them based on multi-scale information to match high-resolution features. Additionally, we construct a cross-class alignment (CCA) module to solve the problem of the mismatch of class numbers. By combining an easy-to-hard training (ETHT) strategy, the CCA module further enhances the distillation performance. The effectiveness and efficiency of our approach are demonstrated by extensive experiments on two common benchmark datasets: MPII and COCO. The code is made available in supplementary material.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Artificial Behavior Intelligence: Technology, Challenges, and Future Directions
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
SpatialTrackerV2: 3D Point Tracking Made Easy
GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
토론
이 논문과 연결된 포럼 글이 아직 없습니다.