Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
arXiv:2103.13894 · doi:10.1007/S00138-020-01090-5
Abstract
In this work, we present a new, algorithm for multi-domain learning. Given a pretrained architecture and a set of visual domains received sequentially, the goal of multi-domain learning is to produce a single model performing a task in all the domains together. Recent works showed how we can address this problem by masking the internal weights of a given original conv-net through learned binary variables. In this work, we provide a general formulation of binary mask based models for multi-domain learning by affine transformations of the original network parameters. Our formulation obtains significantly higher levels of adaptation to new domains, achieving performances comparable to domain-specific models while requiring slightly more than 1 bit per network parameter per additional domain. Experiments on two popular benchmarks showcase the power of our approach, achieving performances close to state-of-the-art methods on the Visual Decathlon Challenge.
Accepted for publication by Machine Vision and Applications on May 21, 2020. arXiv admin note: substantial text overlap with arXiv:1805.11119
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distilling the Knowledge in a Neural Network
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Fully Convolutional Networks for Semantic Segmentation
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature