paper-with-me

Papers

KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo

2022-07-21 · Yikang Ding, Qingtian Zhu, Xiangyue Liu, Wentao Yuan, Haotian Zhang, Chi Zhang

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth. In this paper, we propose a novel self-supervised training pipeline for MVS based on knowledge distillation, termed KD-MVS, which mainly consists of self-supervised teacher training and distillation-based student training. Specifically, the teacher model is trained in a self-supervised fashion using both photometric and featuremetric consistency. Then we distill the knowledge of the teacher model to the student model through probabilistic knowledge transferring. With the supervision of validated knowledge, the student model is able to outperform its teacher by a large margin. Extensive experiments performed on multiple datasets show our method can even outperform supervised methods.

📄 PDF Abstract BibTeX arXiv:2207.10425

Code (1)

megvii-research/kd-mvs 공식 구현 pytorch

Tasks

Knowledge DistillationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation

2023-03-21 · Vitaliy Kinakh, Mariia Drozdova, Slava Voloshynovskiy

We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings…

ClusteringContrastive LearningKnowledge DistillationLinear evaluation+3

On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation

2023-07-06 · Gene-Ping Yang, Yue Gu, Qingming Tang, Dongsu Du 외

Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in keyword spotting. To address this, we pr…

Keyword SpottingKnowledge DistillationRepresentation LearningSpeech Representation Learning

A Novel Self-Knowledge Distillation Approach with Siamese Representation Learning for Action Recognition

2022-09-03 · Duc-Quang Vu, Trang Phung, Jia-Ching Wang

Knowledge distillation is an effective transfer of knowledge from a heavy network (teacher) to a small network (student) to boost students' performance. Self-knowledge distillation, the special case of knowledge distilla…

Action RecognitionKnowledge DistillationRepresentation LearningSelf-Knowledge Distillation

Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

2023-04-13 · CVPR 2023 1 · Kaiyou Song, Jin Xie, Shan Zhang, Zimeng Luo

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small model…

Knowledge DistillationRepresentation LearningSelf-Supervised Learning

Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving

2026-07-23 · Mengshi Qi, Xiaoyang Bi, Xianlin Zhang, Huadong Ma arxiv

Self-supervised depth estimation is challenging for safe autonomous driving under various adverse weather conditions due to sensor perception degradation. These challenges arise from two main aspects. Firstly, adverse co…

Knowledge DistillationAutonomous DrivingDepth Estimation