A Memory-Assisted Knowledge Transferring Framework with Curriculum Anticipation for Weakly Supervised Online Activity Detection

Engineering, Electrical Engineering, Information Science, Electronic Information, Computer Science, Artificial Intelligence,
weakly supervised learning   online activity detection   knowledge distillation   memory networks   curriculum learning  

Research Background and Significance In recent years, weakly supervised online activity detection (WS-OAD), as an important topic in high-level video understanding, has garnered widespread attention. Its primary goal is to detect ongoing activities frame-by-frame in streaming videos using only inexpensive video-level annotations. This task holds si...

Sample Correlation for Fingerprinting Deep Face Recognition

Information Science, Computer Science, Automation, Artificial Intelligence,
sample correlation   deep face recognition   model fingerprinting   model stealing attacks   JPEG compression   intellectual property protection   knowledge distillation  

Report on Academic Paper: “Sample Correlation for Fingerprinting Deep Face Recognition” Background and Research Problem In recent years, the rapid advancements in deep learning technologies have significantly propelled the development of face recognition. However, commercial face recognition models face increasing intellectual property (IP) threats...

Noninvasive Grading of Glioma by Knowledge Distillation Based Lightweight Convolutional Neural Network

Information Science, Artificial Intelligence, Medicine, Neurosurgery, Oncology,
knowledge distillation   glioma grading   convolutional neural network   lightweight model   image classification  

Review of Non-Invasive Glioma Grading Research: Lightweight Convolutional Neural Networks Based on Knowledge Distillation Background Gliomas are the main tumors of the central nervous system, and early detection is crucial. The World Health Organization (WHO) classifies gliomas from grade I to IV, with grades I and II being low-grade gliomas (LGG) ...

Exploring Adaptive Inter-Sample Relationship in Data-Free Knowledge Distillation

Information Science, Artificial Intelligence,
data-free knowledge distillation   unsupervised representation learning   knowledge distillation   adaptive methods   inter-sample relationship  

In recent years, applications such as privacy protection and large-scale data transmission have posed significant challenges to the inaccessibility of data. Researchers have proposed Data-Free Knowledge Distillation (DFKD) methods to address these issues. Knowledge Distillation (KD) is a method for training a lightweight model (student model) to le...

Prototype-Based Sample-Weighted Distillation Unified Framework Adapted to Missing Modality Sentiment Analysis

Prototype-Based Sample-Weighted Distillation Unified Framework Adapted to Missing Modality Sentiment Analysis

Information Science, Automation, Artificial Intelligence, Humanities and Others,
missing modality   sentiment analysis   knowledge distillation   prototype network   multimodal optimization  

Application of a Prototype-Based Sample Weighted Distillation Unified Framework in Missing Modality Sentiment Analysis Research Background Sentiment analysis is a significant field in Natural Language Processing (NLP). With the development of social media platforms, people increasingly tend to express their emotions through short video clips. This ...

Balancing Feature Alignment and Uniformity for Few-Shot Classification

Balancing Feature Alignment and Uniformity for Few-Shot Classification

Information Science, Artificial Intelligence,
few-shot learning   mutual information   feature representation   knowledge distillation   self-supervised augmentation  

Solving Few-Shot Classification Problems with Balanced Feature Alignment and Uniformity Background and Motivation The goal of Few-Shot Learning (FSL) is to correctly recognize new samples with only a few examples from new classes. Existing few-shot learning methods mainly learn transferable knowledge from base classes by maximizing the information ...

Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching

Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching

Information Science, Artificial Intelligence,
weakly supervised learning   semantic segmentation   knowledge distillation   dual teaching   pseudo segmentation masks  

Weakly Supervised Semantic Image Segmentation via Alternate Self-Dual Teaching Background Introduction With the continuous development of the computer vision field, semantic segmentation has become an important and active research direction. Traditional semantic segmentation methods rely on manually labeled pixel-level tags; however, obtaining thes...