23 citations · 86 across the 16 of their papers we have counts for
5 papers · 1 filter
Fine-Tuning is Fine, if Calibrated
Zheda Mai, Arpita Chowdhury, Ping Zhang +8
Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing…
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
Cheng-Hao Tu, Hong-You Chen, Zheda Mai +7
We propose a learning problem involving adapting a pre-trained source model to the target domain for classifying all classes that appeared in the source data, using target data tha…
Learning Sparse Mixture of Experts for Visual Question Answering
Vardaan Pahuja, Jie Fu, Christopher J. Pal
There has been a rapid progress in the task of Visual Question Answering with improved model architectures. Unfortunately, these models are usually computationally intensive due to…
Structure Learning for Neural Module Networks
Vardaan Pahuja, Jie Fu, Sarath Chandar +1
Neural Module Networks, originally proposed for the task of visual question answering, are a class of neural network architectures that involve human-specified neural modules, each…
Memory Augmented Self-Play
Shagun Sodhani, Vardaan Pahuja
Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the se…