paper-with-me

Papers

Blind Knowledge Distillation for Robust Image Classification

2022-11-21 · Timo Kaiser, Lukas Ehmann, Christoph Reinders, Bodo Rosenhahn

Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of noisy samples in the latter ones. We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting. Based on this, we enable the estimation of noise in the training data with Otsus algorithm. With this estimation, we train the network with a modified weighted cross-entropy loss function. We show in our experiments that Blind Knowledge Distillation detects overfitting effectively during training and improves the detection of clean and noisy labels on the recently published CIFAR-N dataset. Code is available at GitHub.

📄 PDF Abstract BibTeX arXiv:2211.11355

Code (1)

timok93/blind_knowledge_distillation 공식 구현 pytorch

Tasks

Classificationimage-classificationImage ClassificationKnowledge DistillationLearning with noisy labels

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Knowledge Distillation based Degradation Estimation for Blind Super-Resolution

2022-11-30 · Bin Xia, Yulun Zhang, Yitong Wang, Yapeng Tian 외

Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from its corresponding low-resolution (LR) input image with unknown degradations. Most of the existing works design an explicit degrada…

Blind Super-ResolutionImage Super-ResolutionKnowledge DistillationSuper-Resolution

Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment

2025-01-01 · CVPR 2025 1 · Xudong Li, Wenjie Nie, Yan Zhang, Runze Hu 외

In the Blind Image Quality Assessment (BIQA) field, accurately assessing the quality of authentically distorted images presents a substantial challenge due to the diverse distortion types in natural settings. Existin…

Blind Image Quality AssessmentImage Quality AssessmentKnowledge DistillationLocal Distortion

Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment

2021-08-18 · ICCV 2021 10 · Heliang Zheng, Huan Yang, Jianlong Fu, Zheng-Jun Zha 외

An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their correspo…

Image Quality AssessmentImage RestorationKnowledge Distillation

Monitored Distillation for Positive Congruent Depth Completion

2022-03-30 · Tian Yu Liu, Parth Agrawal, Allison Chen, Byung-Woo Hong 외

We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an …

Depth CompletionImage ReconstructionKnowledge DistillationModel Selection

Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation

2023-05-08 · Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Jialu Liu 외

Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output d…

Knowledge Distillation