Robust Feature

Robust feature learning aims to develop machine learning models that are resilient to noise, variations, and adversarial attacks, ensuring reliable performance across diverse datasets and conditions. Current research focuses on improving feature extraction through techniques like adversarial training, contrastive learning, and the application of architectures such as Vision Transformers and Convolutional Neural Networks, often incorporating innovative loss functions and data augmentation strategies. This work is crucial for enhancing the reliability and generalizability of machine learning models in various applications, from medical image analysis and autonomous driving to human activity recognition and robust computer vision tasks. The ultimate goal is to create more dependable and trustworthy AI systems.

Papers

October 21, 2024

Robust Feature Learning for Multi-Index Models in High Dimensions
Alireza Mousavi-Hosseini, Adel Javanmard, Murat A. Erdogdu
Adversarial Perturbation Robust Learning High Dimension Adversarial Scenario Robust Feature Multi Index Model

August 28, 2024

Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection
Sondos Mohamed, Walter Zimmer, Ross Greer, Ahmed Alaaeldin Ghita, Modesto Castrillón-Santana, Mohan Trivedi, Alois Knoll, Salvatore Mario Carta, Mirko Marras
Transfer Learning Monocular 3D Object Detection Monocular Image R CNN Traffic Rule Real World Scene Robust Feature

February 13, 2024

Adversarially Robust Feature Learning for Breast Cancer Diagnosis
Degan Hao, Dooman Arefan, Margarita Zuley, Wendie Berg, Shandong Wu
Adversarial Data Breast Cancer Diagnosis Robust Feature

November 2, 2023

Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning
Jayateja Kalla, Soma Biswas
Incremental Learning Tail Class Robust Feature Classifier Alignment

July 11, 2023

Stochastic Nested Compositional Bi-level Optimization for Robust Feature Learning
Xuxing Chen, Krishnakumar Balasubramanian, Saeed Ghadimi
Stochastic Gradient Stochastic Approximation Compositional Optimization Robust Feature Compositional Nature Stochastic First Order Oracle

July 10, 2023

Robust Feature Learning Against Noisy Labels
Tsung-Ming Tai, Yun-Jie Jhang, Wen-Jyi Hwang
Supervised Learning Noisy Label Bootstrapping End to End Robust Clustering Robust Feature Robust Feature Representation

June 4, 2023

Towards Robust Feature Learning with t-vFM Similarity for Continual Learning
Bilan Gao, YoungBin Kim
Continual LEArning Contrastive Loss Robust Representation Supervised Contrastive Loss Similarity Score Similarity Metric Robust Feature

May 30, 2023

A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play
Deepayan Sanyal, Joel Michelson, Yuan Yang, James Ainooson, Maithilee Kunda
Self Supervised Egocentric Video Self Supervised Contrastive Learning Visual Learning Similar Representation Robust Feature Computational Account

April 14, 2023

DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski
Computer Vision Image Datasets Self Supervised Method Visual Feature Self Supervised Task Robust Feature DINOv2 Model

March 31, 2023

WSense: A Robust Feature Learning Module for Lightweight Human Activity Recognition
Ayokunle Olalekan Ige, Mohd Halim Mohd Noor
Action Recognition Activity Recognition Wearable Sensor Data Accelerometer Signal Robust Feature

February 2, 2023

Exploring Invariant Representation for Visible-Infrared Person Re-Identification
Lei Tan, Yukang Zhang, Shengmei Shen, Yan Wang, Pingyang Dai, Xianming Lin, Yongjian Wu, Rongrong Ji
Person Re Identification Invariant Representation Visible Infrared Person Re Identification Robust Feature Image Data Augmentation Center Loss

August 4, 2022

MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth
Chenjie Cao, Xinlin Ren, Yanwei Fu
Vision Transformer Large Depth Pre Trained Convolutional Neural Network Mono to Stereo Learning Based Multi View Stereo Feature Representation Learning Robust Feature Vanilla Convolutional Neural Network

July 18, 2022

Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric P. Xing
Native Robustness Data Annotation Image Classification Model Robust Feature High OOD Robustness

June 11, 2022

Improving the Adversarial Robustness of NLP Models by Information Bottleneck
Cenyuan Zhang, Xiang Zhou, Yixin Wan, Xiaoqing Zheng, Kai-Wei Chang, Cho-Jui Hsieh
Adversarial Example Adversarial Robustness Information Bottleneck NLP Model Robust Feature Non Robust Feature

January 20, 2022

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification
Xiangyang Zhu, Kede Ma, Wufeng Xue
Left Ventricular Ventricle Segmentation Pyramid Vision Transformer Robust Feature Robust Convolutional Neural Network Robustness Measurement

December 28, 2021

Skin feature point tracking using deep feature encodings
Jose Ramon Chang, Torbjörn E. M. Nordling
Robust Feature Feature Tracking Facial Keypoint Skin Feature

Robust Feature

Papers

Robust Feature Learning for Multi-Index Models in High Dimensions

Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection

Adversarially Robust Feature Learning for Breast Cancer Diagnosis

Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning

Stochastic Nested Compositional Bi-level Optimization for Robust Feature Learning

Robust Feature Learning Against Noisy Labels

Towards Robust Feature Learning with t-vFM Similarity for Continual Learning

A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play

DINOv2: Learning Robust Visual Features without Supervision

WSense: A Robust Feature Learning Module for Lightweight Human Activity Recognition

Exploring Invariant Representation for Visible-Infrared Person Re-Identification

MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth

Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning

Improving the Adversarial Robustness of NLP Models by Information Bottleneck

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification

Skin feature point tracking using deep feature encodings