b'De-Chuan Zhan'

research

∙ 09/13/2023

PILOT: A Pre-Trained Model-Based Continual Learning Toolbox

While traditional machine learning can effectively tackle a wide range o...

0 Hai-Long Sun, et al. ∙

research

∙ 08/17/2023

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

The rapid expansion of foundation pre-trained models and their fine-tune...

0 Yi-Kai Zhang, et al. ∙

research

∙ 07/14/2023

Streaming CTR Prediction: Rethinking Recommendation Task for Real-World Streaming Data

The Click-Through Rate (CTR) prediction task is critical in industrial r...

0 Qi-Wei Wang, et al. ∙

research

∙ 06/19/2023

SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models

Model-based imitation learning (MBIL) is a popular reinforcement learnin...

0 Shenghua Wan, et al. ∙

research

∙ 06/08/2023

COURIER: Contrastive User Intention Reconstruction for Large-Scale Pre-Train of Image Features

With the development of the multi-media internet, visual characteristics...

0 Jia-Qi Yang, et al. ∙

research

∙ 06/08/2023

Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping

Research has shown that deep networks tend to be overly optimistic about...

0 Jia-Qi Yang, et al. ∙

research

∙ 06/06/2023

Model Spider: Learning to Rank Pre-Trained Models Efficiently

Figuring out which Pre-Trained Model (PTM) from a model zoo fits the tar...

0 Yi-Kai Zhang, et al. ∙

research

∙ 05/30/2023

Learning without Forgetting for Vision-Language Models

Class-Incremental Learning (CIL) or continual learning is a desired capa...

0 Da-Wei Zhou, et al. ∙

research

∙ 05/30/2023

IDToolkit: A Toolkit for Benchmarking and Developing Inverse Design Algorithms in Nanophotonics

Aiding humans with scientific designs is one of the most exciting of art...

0 Jia-Qi Yang, et al. ∙

research

∙ 05/07/2023

MrTF: Model Refinery for Transductive Federated Learning

We consider a real-world scenario in which a newly-established pilot pro...

0 Xin-Chun Li, et al. ∙

research

∙ 04/14/2023

Preserving Locality in Vision Transformers for Class Incremental Learning

Learning new classes without forgetting is crucial for real-world applic...

0 Bowen Zheng, et al. ∙

research

∙ 04/11/2023

The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting

Multivariate time series data comprises various channels of variables. T...

0 Lu Han, et al. ∙

research

∙ 03/13/2023

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need

Class-incremental learning (CIL) aims to adapt to emerging new classes w...

0 Da-Wei Zhou, et al. ∙

research

∙ 02/07/2023

Deep Class-Incremental Learning: A Survey

Deep models, e.g., CNNs and Vision Transformers, have achieved impressiv...

0 Da-Wei Zhou, et al. ∙

research

∙ 01/15/2023

On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning

When there are unlabeled Out-Of-Distribution (OOD) data from other class...

0 Lu Han, et al. ∙

research

∙ 01/05/2023

Self-Motivated Multi-Agent Exploration

In cooperative multi-agent reinforcement learning (CMARL), it is critica...

0 Shaowei Zhang, et al. ∙

research

∙ 06/17/2022

Avoid Overfitting User Specific Information in Federated Keyword Spotting

Keyword spotting (KWS) aims to discriminate a specific wake-up word from...

0 Xin-Chun Li, et al. ∙

research

∙ 06/01/2022

Contrastive Principal Component Learning: Modeling Similarity by Augmentation Overlap

Traditional self-supervised contrastive learning methods learn embedding...

0 Lu Han, et al. ∙

research

∙ 06/01/2022

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Predicting conversion rate (e.g., the probability that a user will purch...

0 Jia-Qi Yang, et al. ∙

research

∙ 05/26/2022

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

Real-world applications require the classification model to adapt to new...

0 Da-Wei Zhou, et al. ∙

research

∙ 05/04/2022

Generalized Knowledge Distillation via Relationship Matching

The knowledge of a well-trained deep neural network (a.k.a. the "teacher...

8 Han-Jia Ye, et al. ∙

research

∙ 04/25/2022

Faculty Distillation with Optimal Transport

Knowledge distillation (KD) has shown its effectiveness in improving a s...

0 Su Lu, et al. ∙

research

∙ 04/10/2022

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

The ability to learn new concepts continually is necessary in this ever-...

0 Fu-Yun Wang, et al. ∙

research

∙ 04/08/2022

Identifying Ambiguous Similarity Conditions via Semantic Matching

Rich semantics inside an image result in its ambiguous relationship with...

0 Han-Jia Ye, et al. ∙

research

∙ 03/31/2022

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

New classes arise frequently in our ever-changing world, e.g., emerging ...

0 Da-Wei Zhou, et al. ∙

research

∙ 03/28/2022

Federated Learning with Position-Aware Neurons

Federated Learning (FL) fuses collaborative models from local nodes with...

0 Xin-Chun Li, et al. ∙

research

∙ 03/14/2022

Forward Compatible Few-Shot Class-Incremental Learning

Novel classes frequently arise in our dynamically changing world, e.g., ...

0 Da-Wei Zhou, et al. ∙

research

∙ 12/23/2021

PyCIL: A Python Toolbox for Class-Incremental Learning

Traditional machine learning systems are deployed under the closed-world...

0 Da-Wei Zhou, et al. ∙

research

∙ 12/07/2021

RID-Noise: Towards Robust Inverse Design under Noisy Environments

From an engineering perspective, a design should not only perform well i...

0 Jia-Qi Yang, et al. ∙

research

∙ 09/26/2021

LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates

In cooperative multi-agent reinforcement learning (MARL), where agents o...

0 Jiahan Cao, et al. ∙

research

∙ 07/27/2021

Co-Transport for Class-Incremental Learning

Traditional learning systems are trained in closed-world for a fixed num...

0 Da-Wei Zhou, et al. ∙

research

∙ 07/26/2021

Preliminary Steps Towards Federated Sentiment Classification

Automatically mining sentiment tendency contained in natural language is...

0 Xin-Chun Li, et al. ∙

research

∙ 07/26/2021

Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes

Although federated learning (FL) has recently been proposed for efficien...

0 Xin-Chun Li, et al. ∙

research

∙ 07/01/2021

Few-Shot Learning with a Strong Teacher

Few-shot learning (FSL) aims to train a strong classifier using limited ...

0 Han-Jia Ye, et al. ∙

research

∙ 06/15/2021

Contextualizing Multiple Tasks via Learning to Decompose

One single instance could possess multiple portraits and reveal diverse ...

5 Han-Jia Ye, et al. ∙

research

∙ 04/17/2021

Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport

Complex objects are usually with multiple labels, and can be represented...

0 Yang Yang, et al. ∙

research

∙ 04/08/2021

Few-Shot Action Recognition with Compromised Metric via Optimal Transport

Although vital to computer vision systems, few-shot action recognition i...

0 Su Lu, et al. ∙

research

∙ 04/08/2021

Support-Target Protocol for Meta-Learning

The support/query (S/Q) training protocol is widely used in meta-learnin...

0 Su Lu, et al. ∙

research

∙ 04/05/2021

Procrustean Training for Imbalanced Deep Learning

Neural networks trained with class-imbalanced data are known to perform ...

0 Han-Jia Ye, et al. ∙

research

∙ 03/28/2021

Learning Placeholders for Open-Set Recognition

Traditional classifiers are deployed under closed-set setting, with both...

0 Da-Wei Zhou, et al. ∙

research

∙ 11/30/2020

Revisiting Unsupervised Meta-Learning: Amplifying or Compensating for the Characteristics of Few-Shot Tasks

Meta-learning becomes a practical approach towards few-shot image classi...

0 Han-Jia Ye, et al. ∙

research

∙ 02/03/2020

Revisiting Meta-Learning as Supervised Learning

Recent years have witnessed an abundance of new publications and approac...

0 Wei-Lun Chao, et al. ∙

research

∙ 01/06/2020

Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning

We investigate learning a ConvNet classifier with class-imbalanced data....

0 Han-Jia Ye, et al. ∙

research

∙ 06/07/2019

Learning Classifier Synthesis for Generalized Few-Shot Learning

Visual recognition in real-world requires handling long-tailed and even ...

9 Han-Jia Ye, et al. ∙

research

∙ 12/10/2018

Learning Embedding Adaptation for Few-Shot Learning

Learning with limited data is a key challenge for visual recognition. Fe...

18 Han-Jia Ye, et al. ∙

De-Chuan Zhan

Featured Co-authors