Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning

Abstract

Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data. In this scheme, a target learning task with insufficient training data is carried out simultaneously with another source learning task with abundant training data. However, the source learning task does not use all existing training data. Our core idea is to identify and use a subset of training images from the original source learning task whose low-level characteristics are similar to those from the target learning task, and jointly fine-tune shared convolutional layers for both tasks. Specifically, we compute descriptors from linear or nonlinear filter bank responses on training images from both tasks, and use such descriptors to search for a desired subset of training samples for the source learning task. Experiments demonstrate that our selective joint fine-tuning scheme achieves state-of-the-art performance on multiple visual classification tasks with insufficient training data for deep learning. Such tasks include Caltech 256, MIT Indoor 67, Oxford Flowers 102 and Stanford Dogs 120. In comparison to fine-tuning without a source domain, the proposed method can improve the classification accuracy by 2% - 10% using a single model.

To appear in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Learning Transferable Features with Deep Adaptation Networks
• Going Deeper with Convolutions
• Fully Convolutional Networks for Semantic Segmentation
• Identity Mappings in Deep Residual Networks
• Understanding Deep Image Representations by Inverting Them
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition

Cited by in corpus (7)

• Deep Visual Domain Adaptation: A Survey
• Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data
• An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
• Optimal Transport for Deep Joint Transfer Learning
• Building Graph Representations of Deep Vector Embeddings
• Channel Interaction Networks for Fine-Grained Image Categorization
• Transfer Learning in CNNs Using Filter-Trees