Class Interference

Class interference, the difficulty deep learning models face in distinguishing between similar classes, is a significant hurdle in various applications, including anomaly detection and image recognition. Current research focuses on mitigating this interference through techniques like attention mechanisms that filter irrelevant information, class-aware models that leverage label information to improve discrimination, and uncertainty-based methods that refine class boundaries. Addressing class interference is crucial for improving the accuracy and efficiency of deep learning models across diverse fields, leading to more robust and reliable systems in areas such as industrial monitoring and GNSS signal processing.

Papers

November 4, 2024

Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task
Hoonick Lee, Mogan Gim, Donghyeon Park, Donghee Choi, Jaewoo Kang
Large Language Model Recipe Generation Class Interference Ash Cloud

May 10, 2024

Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection
Sushovan Jena, Vishwas Saini, Ujjwal Shaw, Pavitra Jain, Abhay Singh Raihal, Anoushka Banerjee, Sharad Joshi, Ananth Ganesh, Arnav Bhavsar
Anomaly Detection Unsupervised Anomaly Detection Convolutional Block Attention Multi Class Anomaly Detection Attention Distillation Class Interference

March 21, 2024

Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
Xi Jiang, Ying Chen, Qiang Nie, Jianlin Liu, Yong Liu, Chengjie Wang, Feng Zheng
Anomaly Detection Neural Implicit Representation Multi Class Anomaly Detection Class Representation Class Interference

February 9, 2024

Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data
Felix Ott, Lucas Heublein, Nisha Lakshmana Raichur, Tobias Feigl, Jonathan Hansen, Alexander Rügamer, Christopher Mutschler
LeArning Abstract Shot Learning Catastrophic Interference Jamming Detection Class Interference

September 23, 2023

Early-Exit with Class Exclusion for Efficient Inference of Neural Networks
Jingcun Wang, Bing Li, Grace Li Zhang
Neural Network Deep Neural Network Efficient Inference Early eXit Early Exit Dynamic Inference Class Interference

October 31, 2022

Class Interference of Deep Neural Networks
Dongcui Diao, Hengshuai Yao, Bei Jiang
Deep Neural Network Deep Network Generalization Error Network Interference Class Interference

October 15, 2022

Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices
Navidreza Asadi, Maziar Goudarzi
Convolutional Neural Network Scientific Inference Internet of Thing Device Resource Constrained Model Parallelism Real Time Inference Expert Parallelism Class Interference

March 7, 2022

On the pitfalls of entropy-based uncertainty for multi-class semi-supervised segmentation
Martin Van Waerebeke, Gregory Lodygensky, Jose Dolz
Semi Supervised Learning Deep Model Common Pitfall Segmentation Uncertainty Entropy Based Multi Class Segmentation Multiclass Segmentation Class Interference

Class Interference

Papers

Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task

Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection

Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference

Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data

Early-Exit with Class Exclusion for Efficient Inference of Neural Networks

Class Interference of Deep Neural Networks

Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices

On the pitfalls of entropy-based uncertainty for multi-class semi-supervised segmentation