Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions
Tian Jin, Zhun Liu, Shengjia Yan, Alexandre Eichenberger, Louis-Philippe Morency
NLP Applications Long Paper
Session 12A: Jul 8
(08:00-09:00 GMT)
Session 13A: Jul 8
(12:00-13:00 GMT)
Abstract:
Transfer learning using ImageNet pre-trained models has been the de facto approach in a wide range of computer vision tasks. However, fine-tuning still requires task-specific training data. In this paper, we propose N³ (Neural Networks from Natural Language) - a new paradigm of synthesizing task-specific neural networks from language descriptions and a generic pre-trained model. N³ leverages language descriptions to generate parameter adaptations as well as a new task-specific classification layer for a pre-trained neural network, effectively ``fine-tuning'' the network for a new task using only language descriptions as input. To the best of our knowledge, N³ is the first method to synthesize entire neural networks from natural language. Experimental results show that N³ can out-perform previous natural-language based zero-shot learning methods across 4 different zero-shot image classification benchmarks. We also demonstrate a simple method to help identify keywords in language descriptions leveraged by N³ when synthesizing model parameters.
You can open the
pre-recorded video
in a separate window.
NOTE: The SlidesLive video may display a random order of the authors.
The correct author list is shown at the top of this webpage.