"teacher-student framework" Papers

12 papers found

HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving

R.D. Lin, Pengcheng Weng, Yinqiao Wang et al.

CVPR 2025arXiv:2503.17752
1
citations

Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection

Marc-Antoine Lavoie, Anas Mahmoud, Steven L. Waslander

CVPR 2025arXiv:2503.23220
6
citations

Learning to Solve Complex Problems via Dataset Decomposition

Wanru Zhao, Lucas Page-Caccia, Zhengyan Shi et al.

NEURIPS 2025

NightHaze: Nighttime Image Dehazing via Self-Prior Learning

Beibei Lin, Yeying Jin, Yan Wending et al.

AAAI 2025paperarXiv:2403.07408
24
citations

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

Quan Zhang, Yuxin Qi, Xi Tang et al.

AAAI 2025paperarXiv:2501.11124
8
citations

Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation

Zhen Zhao, Zicheng Wang, Dian Yu et al.

ECCV 2024arXiv:2311.17325
37
citations

AMD: Automatic Multi-step Distillation of Large-scale Vision Models

Cheng Han, Qifan Wang, Sohail A Dianat et al.

ECCV 2024arXiv:2407.04208
15
citations

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

Yanjing Li, Sheng Xu, Mingbao Lin et al.

AAAI 2024paperarXiv:2305.12354
22
citations

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers

Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson et al.

ICML 2024spotlightarXiv:2402.06323
10
citations

NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction

Beibei Lin, Yeying Jin, Wending Yan et al.

AAAI 2024paperarXiv:2401.00729
23
citations

Robust Synthetic-to-Real Transfer for Stereo Matching

Jiawei Zhang, Jiahe Li, Lei Huang et al.

CVPR 2024arXiv:2403.07705
18
citations

Weak-to-Strong 3D Object Detection with X-Ray Distillation

Alexander Gambashidze, Aleksandr Dadukin, Maksim Golyadkin et al.

CVPR 2024arXiv:2404.00679
6
citations