283 citations · 817 across the 58 of their papers we have counts for
18 papers · 1 filter
Parrot: Multilingual Visual Instruction Tuning
Hai-Long Sun, Da-Wei Zhou, Yang Li +8
The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align…
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen
Da-Wei Zhou, Zhi-Hong Qi, Han-Jia Ye +1
The era of pre-trained models has ushered in a wealth of new insights for the machine learning community. Among the myriad of questions that arise, one of paramount importance is:…
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye +1
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL,…
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang +2
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new class…
Learning without Forgetting for Vision-Language Models
Da-Wei Zhou, Yuanhan Zhang, Yan Wang +4
Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former o…
Class-Incremental Learning: A Survey
Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi +3
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in…
Generalized Knowledge Distillation via Relationship Matching
Han-Jia Ye, Su Lu, De-Chuan Zhan
The knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and in…
Identifying Ambiguous Similarity Conditions via Semantic Matching
Han-Jia Ye, Yi Shi, De-Chuan Zhan
Rich semantics inside an image result in its ambiguous relationship with others, i.e., two images could be similar in one condition but dissimilar in another. Given triplets like "…
Federated Learning with Position-Aware Neurons
Xin-Chun Li, Yi-Chu Xu, Shaoming Song +4
Federated Learning (FL) fuses collaborative models from local nodes without centralizing users' data. The permutation invariance property of neural networks and the non-i.i.d. data…
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye +1
The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categori…
Forward Compatible Few-Shot Class-Incremental Learning
Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye +3
Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without fo…
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
Da-Wei Zhou, Han-Jia Ye, Liang Ma +3
New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and mea…
Co-Transport for Class-Incremental Learning
Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world…
Few-Shot Learning with a Strong Teacher
Han-Jia Ye, Lu Ming, De-Chuan Zhan +1
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can…
Few-Shot Action Recognition with Compromised Metric via Optimal Transport
Su Lu, Han-Jia Ye, De-Chuan Zhan
Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning alg…
Learning Placeholders for Open-Set Recognition
Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input…
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Han-Jia Ye, Lu Han, De-Chuan Zhan
Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be app…
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
Han-Jia Ye, Hexiang Hu, De-Chuan Zhan
Object recognition in the real-world requires handling long-tailed or even open-ended data. An ideal visual system needs to recognize the populated head visual concepts reliably an…