Task Transferability

Task transferability in machine learning focuses on leveraging knowledge learned from one task (source) to improve performance on a different, related task (target), minimizing the need for extensive retraining. Current research emphasizes improving transferability across diverse modalities (image, text, audio, graph data) and tasks (classification, regression, generation), often employing foundation models and techniques like prompt engineering, and exploring the role of feature representations and model architectures (e.g., CNNs, Transformers, NSDEs). This research is crucial for enhancing the efficiency and robustness of machine learning systems, particularly in data-scarce scenarios and applications requiring adaptation to new domains or tasks, such as medical image analysis and robotics.

Papers

December 3, 2023

TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
Xiaojun Jia, Jindong Gu, Yihao Huang, Simeng Qin, Qing Guo, Yang Liu, Xiaochun Cao
Adversarial Attack Semantic Segmentation Adversarial Example Task Transferability Adversarial Text

December 1, 2023

Simple Transferability Estimation for Regression Tasks
Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho, Vu Dinh, Anh T. Tran, Tal Hassner, Cuong V. Nguyen
Transfer Learning Task Transferability Regression Task Transferability Estimation

November 29, 2023

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields
Xiaoliang Liu, Furao Shen, Feng Han, Jian Zhao, Changhai Nie
Adversarial Attack Neural Radiance Field Face Recognition Task Transferability Adversarial Patch UV Mapping Adversarial Face

November 12, 2023

An advantage based policy transfer algorithm for reinforcement learning with metrics of transferability
Md Ferdous Alam, Parinaz Naghizadeh, David Hoelzle
Reinforcement Learning Reinforcement Learning Algorithm Task Transferability Metric Library Advantage Feedback Transfer Reinforcement Learning Policy Transfer

November 1, 2023

October 27, 2023

MELEP: A Novel Predictive Measure of Transferability in Multi-Label ECG Diagnosis
Cuong V. Nguyen, Hieu Minh Duong, Cuong D. Do
Multi Label Task Transferability Electrocardiogram Data Electrocardiogram Analysis Prediction Framework Transferability Metric

October 26, 2023

A Survey on Transferability of Adversarial Examples across Deep Neural Networks
Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqain Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip Torr
Deep Neural Network Timely Survey Adversarial Example Task Transferability Adversarial Vulnerability

October 23, 2023

Unlocking the Transferability of Tokens in Deep Models for Tabular Data
Qi-Le Zhou, Han-Jia Ye, Le-Ye Wang, De-Chuan Zhan
Pre Trained Model Tabular Data Deep Model Task Transferability K TOKEN Tabular Deep Learning Pre Trained Deep Neural Network

October 22, 2023

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu
Adversarial Attack Adversarial Example Task Transferability Adversarial Sample Universal Adversarial

October 21, 2023

On the Transferability of Visually Grounded PCFGs
Yanpeng Zhao, Ivan Titov
Task Transferability Training Domain Grammar Induction

October 16, 2023

On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data
Rongjun Qin, Guixiang Zhang, Yang Tang
Semantic Segmentation Domain Adaptation Remote Sensing Task Transferability Learning Model Transferability Estimation Model Transferability

October 2, 2023

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model
Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal, Raphael Olivier, Ankit Shah, Joseph Konan, Dareen Alharthi, Hazim T Bukhari, Massa Baali, Soham Deshmukh, Michael Kuhlmann, Bhiksha Raj, Rita Singh
Large Language Model Adversarial Attack Fine Tuning Task Transferability Transferable Attack Private Model Adversarial Suffix Proxy Model Proxy Tuning

September 27, 2023

September 4, 2023

Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration
Fengfan Zhou, Hefei Ling, Yuxuan Shi, Jiazhong Chen, Ping Li
Adversarial Attack Adversarial Perturbation Face Recognition Task Transferability Visual Quality Face Restoration Restoration Network Adversarial Face

August 27, 2023

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy
Chengrui Gao, Haopu Shang, Ke Xue, Dong Li, Chao Qian
Diverse Ensemble Task Transferability Neural Solver Vehicle Routing Problem Local Level NP Hard Combinatorial Optimization Problem Neural Construction VRP Variant

August 21, 2023

August 11, 2023

Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance
Huiwen Xu, U Kang
Transfer Learning Pre Trained Model Task Transferability Pre Ranking Transferability Measure

Task Transferability

Papers

TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation

Simple Transferability Estimation for Regression Tasks

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields

An advantage based policy transfer algorithm for reinforcement learning with metrics of transferability

GIST: Generated Inputs Sets Transferability in Deep Learning

Transferability and explainability of deep learning emulators for regional climate model projections: Perspectives for future applications

MELEP: A Novel Predictive Measure of Transferability in Multi-Label ECG Diagnosis

A Survey on Transferability of Adversarial Examples across Deep Neural Networks

Unlocking the Transferability of Tokens in Deep Models for Tabular Data

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability

On the Transferability of Visually Grounded PCFGs

On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs

Transferability of Representations Learned using Supervised Contrastive Learning Trained on a Multi-Domain Dataset

Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy

Enhancing Adversarial Attacks: The Similar Target Method

Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer

Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance