Current state-of-the-art results in computer vision depend in part on
fi...
Recent studies have shown that dual encoder models trained with the
sent...
Masked Image Modeling (MIM) achieves outstanding success in self-supervi...
Despite that going deep has proven successful in many neural architectur...
In continual learning, model needs to continually learn a feature extrac...
Recent work has explored the potential to adapt a pre-trained vision
tra...
The pretrain-then-finetune paradigm has been widely adopted in computer
...
Deep learning models have achieved great success in many fields, yet the...
Continual learning requires the model to maintain the learned knowledge ...
We study a practical setting of continual learning: fine-tuning on a
pre...
Contrastive learning between different views of the data achieves outsta...
Session-based recommendation tries to make use of anonymous session data...
Few-shot classification aims to recognize unseen classes with few labele...
Collaborative Filtering (CF) based recommendation methods have been wide...
The performance of meta-learning approaches for few-shot learning genera...
Lifelong or continual learning remains to be a challenge for artificial
...
The ability of intelligent agents to learn and remember multiple tasks
s...
Autoregressive sequence models achieve state-of-the-art performance in
d...
We propose Dynamically Pruned Message Passing Networks (DPMPN) for
large...
In this paper, a new data structure named group-list is proposed. The
gr...
The ability of reasoning beyond data fitting is substantial to deep lear...
Recurrent Neural Networks (RNNs) are widely used in the field of natural...
Keyphrase extraction from documents is useful to a variety of applicatio...
We study the problem of learning representations of entities and relatio...
In general, recommendation can be viewed as a matching problem, i.e., ma...
Previous traditional approaches to unsupervised Chinese word segmentatio...
Recursive Neural Network (RecNN), a type of models which compose words o...