Deep Model

Deep models, encompassing a broad range of neural network architectures, aim to learn complex patterns from data for various tasks like image classification, time series forecasting, and system identification. Current research emphasizes improving efficiency (e.g., through constant-time learning algorithms and layer caching), enhancing explainability (e.g., via gradient-free methods), and mitigating issues like bias and memorization. These advancements are significant because they improve the reliability, trustworthiness, and applicability of deep models across diverse scientific fields and real-world applications, including healthcare, finance, and autonomous systems.

Papers

November 11, 2024

Learning from Limited and Imperfect Data
Harsh Rangwani
LeArning Abstract Deep Model Long Tail Tail Class Learning Generative Model

November 7, 2024

Impact of Label Noise on Learning Complex Features
Rahul Vashisht, P. Krishna Kumar, Harsha Vardhan Govind, Harish G. Ramaswamy
Gradient Descent Global Impact Stochastic Gradient Descent Label Noise Deep Model Pre Training Model Explicit Regularization

November 4, 2024

October 17, 2024

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
Guibin Zhang, Haonan Dong, Yuchen Zhang, Zhixun Li, Dingshuo Chen, Kai Wang, Tianlong Chen, Yuxuan Liang, Dawei Cheng, Kun Wang
Native Robustness High Efficiency Deep Model Balancing Strategy Data Pruning GNN Backbone Dataset Pruning Graph Pruning

October 16, 2024

SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques
Arham Khan, Todd Nief, Nathaniel Hudson, Mansi Sakarvadia, Daniel Grzenda, Aswathy Ajith, Jordan Pettyjohn, Kyle Chard, Ian Foster
Deep Learning Model Deep Model Internal Representation Loss Landscape Model Merging Common Ground

October 15, 2024

Leveraging Structure Knowledge and Deep Models for the Detection of Abnormal Handwritten Text
Zi-Rui Wang
Data Detection Deep Model Handwritten Text Structural Knowledge Handwritten Character Handwritten Text Image

October 8, 2024

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
Mohammadreza Salehi, Jae Sung Park, Tanush Yadav, Aditya Kusupati, Ranjay Krishna, Yejin Choi, Hannaneh Hajishirzi, Ali Farhadi
Action Recognition Deep Model Multimodal Foundation Model Video Question VideoQA Benchmark

October 3, 2024

Learning K-U-Net with constant complexity: An Application to time series forecasting
Jiang You, Arben Cela, René Natowicz, Jacob Ouanounou, Patrick Siarry
LeArning Abstract Deep Learning Model Application Proficiency Time Series Stochastic Gradient Descent Time Series Forecasting Complexity Matter Deep Model

September 17, 2024

Gradient-free Post-hoc Explainability Using Distillation Aided Learnable Approach
Debarpan Bhattacharya, Amir H. Poorjam, Deepak Mittal, Sriram Ganapathy
High Explainability Deep Model Saliency Explanation Post Hoc Explainability

September 10, 2024

EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
Suorong Yang, Furao Shen, Jian Zhao
Data Augmentation Image Classification Deep Model Cross Entropy Loss Perturbation Augmentation Augmentation Operation

August 23, 2024

Say No to Freeloader: Protecting Intellectual Property of Your Deep Model
Lianyu Wang, Meng Wang, Huazhu Fu, Daoqiang Zhang
Deep Model Internet Service Domain Unlabeled Target Domain Domain Discriminator Intellectual Property

August 18, 2024

Say My Name: a Model's Bias Discovery Framework
Massimiliano Ciranni, Luca Molinaro, Carlo Alberto Barbano, Attilio Fiandrotti, Vittorio Murino, Vito Paolo Pastore, Enzo Tartaglione
Full Model Pseudo Label Deep Model Name Translation Bias Detection Potential Bias Biased Feature Pseudo Bias

August 17, 2024

StylePrompter: Enhancing Domain Generalization with Test-Time Style Priors
Jiao Zhang, Jian Xu, Xu-Yao Zhang, Cheng-Lin Liu
Domain Generalization Deep Model Unseen Domain Temporal Prior

August 7, 2024

Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENN
Chang Yu, Yixin Jin, Qianwen Xing, Ye Zhang, Shaobo Guo, Shuchen Meng
Machine Learning Model High Dimensional Deep Model Risk Prediction XGBoost Model Credit Risk LightGBM Model SMOTE Integrated

July 3, 2024

Modern Neighborhood Components Analysis: A Deep Tabular Baseline Two Decades Later
Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan
Deep Model Tabular Deep Learning Tabular Prediction Neighborhood Component Analysis

July 1, 2024

DCoM: Active Learning for All Learners
Inbal Mishal, Daphna Weinshall
LeArning Abstract Active Learning Deep Model Deep Active Learning Margin Based Coverage Control Novel Active Learning

June 3, 2024

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
Xinyin Ma, Gongfan Fang, Michael Bi Mi, Xinchao Wang
Transformer Model Deep Model Diffusion Transformer Optimization Layer

May 30, 2024

Deep Modeling of Non-Gaussian Aleatoric Uncertainty
Aastha Acharya, Caleb Lee, Marissa D'Alonzo, Jared Shamwell, Nisar R. Ahmed, Rebecca Russell
Deep Model State Estimation Aleatoric Uncertainty Conditional Density Non Gaussian Non Gaussian Aleatoric Uncertainty

May 29, 2024

MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection
Raman Dutt, Ondrej Bohdal, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
Diffusion Model Parameter Efficient Fine Tuning Deep Model Limited Memorization Data Memorization Memorization Capability Verbatim Memorization

Deep Model

Papers

Learning from Limited and Imperfect Data

Impact of Label Noise on Learning Complex Features

Weakly supervised deep learning model with size constraint for prostate cancer detection in multiparametric MRI and generalization to unseen domains

Exploiting Contextual Uncertainty of Visual Data for Efficient Training of Deep Models

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques

Leveraging Structure Knowledge and Deep Models for the Detection of Abnormal Handwritten Text

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition

Learning K-U-Net with constant complexity: An Application to time series forecasting

Gradient-free Post-hoc Explainability Using Distillation Aided Learnable Approach

EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification

Say No to Freeloader: Protecting Intellectual Property of Your Deep Model

Say My Name: a Model's Bias Discovery Framework

StylePrompter: Enhancing Domain Generalization with Test-Time Style Priors

Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENN

Modern Neighborhood Components Analysis: A Deep Tabular Baseline Two Decades Later

DCoM: Active Learning for All Learners

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

Deep Modeling of Non-Gaussian Aleatoric Uncertainty

MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection