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

October 25, 2023

MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
Yinan Liang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu
Vision Transformer Transformer Architecture Deep Model 32 Bit Microcontrollers Limited Memory CNN Inference

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 17, 2023

Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs
Uri Stern, Daphna Weinshall
Deep Neural Network Anti Forgetting Deep Model DNN Framework Training Free Model Overfitting Modern Deep Learning Model

October 13, 2023

It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models
Lin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar
Deep Learning Model Alignment Problem Deep Model Generalization Error Neural Collapse Variance Information

October 4, 2023

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers
KL Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash
Vision Transformer Deep Model Adversarial Patch Transformer Inference Standard Adversarial Training

October 3, 2023

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong Li, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou
Pre Trained Model Deep Model X Ray X Ray Image Continual Pre Training Body Part Medical Imaging Task Self Training Pipeline Self Supervised Continual Learning

October 2, 2023

Progressive DeepSSM: Training Methodology for Image-To-Shape Deep Models
Abu Zahid Bin Aziz, Jadie Adams, Shireen Elhabian
Deep Model Shape Prior Statistical Shape Training Method Anatomical Shape

October 1, 2023

Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology
Lucas Rosenblatt, Bin Han, Erin Posthumus, Theresa Crimmins, Bill Howe
Neural Network Deep Learning Deep Model Multi Modal Model Plant Growth Simulation

September 21, 2023

Precision in Building Extraction: Comparing Shallow and Deep Models using LiDAR Data
Muhammad Sulaiman, Mina Farmanbar, Ahmed Nabil Belbachir, Chunming Rong
Deep Model LiDAR Data Multidimensional Local Precision Rate Building Segmentation Shallow Layer Building Extraction Shallow Water Supervised Segmentation Aware Mask

September 20, 2023

August 30, 2023

Task-Based MoE for Multitask Multilingual Machine Translation
Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P. Woodruff, Barnabas Poczos, Hany Hassan Awadalla
Multi Task Mixture of Expert Deep Model Multilingual Machine Translation Diverse Task Task Specific Adapter

August 21, 2023

August 18, 2023

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
Latent Space Deep Model Topic Bias Gradient Regularization Concept Activation Vector Model Sensitivity Hope Speech

August 7, 2023

DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data
Yancheng Liang, Jiajie Zhang, Hui Li, Xiaochen Liu, Yi Hu, Yong Wu, Jinyao Zhang, Yongyan Liu, Yi Wu
Deep Model Risk Prediction Real World Financial Data

August 2, 2023

Calibration in Deep Learning: A Survey of the State-of-the-Art
Cheng Wang
Deep Learning Timely Survey State of the Art Calibration Performance Deep Model Model Calibration

July 31, 2023

July 19, 2023

Towards Saner Deep Image Registration
Bin Duan, Ming Zhong, Yan Yan
Deep Model Image Registration Deep Learning Based Registration

Deep Model

Papers

MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory

Unlocking the Transferability of Tokens in Deep Models for Tabular Data

Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs

It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts

Progressive DeepSSM: Training Methodology for Image-To-Shape Deep Models

Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology

Precision in Building Extraction: Comparing Shallow and Deep Models using LiDAR Data

Budget-Aware Pruning: Handling Multiple Domains with Less Parameters

PAGER: A Framework for Failure Analysis of Deep Regression Models

Task-Based MoE for Multitask Multilingual Machine Translation

Switched auxiliary loss for robust training of transformer models for histopathological image segmentation

Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space

DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data

Calibration in Deep Learning: A Survey of the State-of-the-Art

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

Towards Saner Deep Image Registration