While traditional machine learning can effectively tackle a wide range o...
The rapid expansion of foundation pre-trained models and their fine-tune...
The Click-Through Rate (CTR) prediction task is critical in industrial
r...
Model-based imitation learning (MBIL) is a popular reinforcement learnin...
With the development of the multi-media internet, visual characteristics...
Research has shown that deep networks tend to be overly optimistic about...
Figuring out which Pre-Trained Model (PTM) from a model zoo fits the tar...
Class-Incremental Learning (CIL) or continual learning is a desired
capa...
Aiding humans with scientific designs is one of the most exciting of
art...
We consider a real-world scenario in which a newly-established pilot pro...
Learning new classes without forgetting is crucial for real-world
applic...
Multivariate time series data comprises various channels of variables. T...
Class-incremental learning (CIL) aims to adapt to emerging new classes
w...
Deep models, e.g., CNNs and Vision Transformers, have achieved impressiv...
When there are unlabeled Out-Of-Distribution (OOD) data from other class...
In cooperative multi-agent reinforcement learning (CMARL), it is critica...
Keyword spotting (KWS) aims to discriminate a specific wake-up word from...
Traditional self-supervised contrastive learning methods learn embedding...
Predicting conversion rate (e.g., the probability that a user will purch...
Real-world applications require the classification model to adapt to new...
The knowledge of a well-trained deep neural network (a.k.a. the "teacher...
Knowledge distillation (KD) has shown its effectiveness in improving a
s...
The ability to learn new concepts continually is necessary in this
ever-...
Rich semantics inside an image result in its ambiguous relationship with...
New classes arise frequently in our ever-changing world, e.g., emerging
...
Federated Learning (FL) fuses collaborative models from local nodes with...
Novel classes frequently arise in our dynamically changing world, e.g., ...
Traditional machine learning systems are deployed under the closed-world...
From an engineering perspective, a design should not only perform well i...
In cooperative multi-agent reinforcement learning (MARL), where agents o...
Traditional learning systems are trained in closed-world for a fixed num...
Automatically mining sentiment tendency contained in natural language is...
Although federated learning (FL) has recently been proposed for efficien...
Few-shot learning (FSL) aims to train a strong classifier using limited
...
One single instance could possess multiple portraits and reveal diverse
...
Complex objects are usually with multiple labels, and can be represented...
Although vital to computer vision systems, few-shot action recognition i...
The support/query (S/Q) training protocol is widely used in meta-learnin...
Neural networks trained with class-imbalanced data are known to perform
...
Traditional classifiers are deployed under closed-set setting, with both...
Meta-learning becomes a practical approach towards few-shot image
classi...
Recent years have witnessed an abundance of new publications and approac...
We investigate learning a ConvNet classifier with class-imbalanced data....
Visual recognition in real-world requires handling long-tailed and even
...
Learning with limited data is a key challenge for visual recognition.
Fe...