Multi-Task Self-Training for Learning General Representations

Abstract

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which harnesses the knowledge in independent specialized teacher models (e.g., ImageNet model on classification) to train a single general student model. Our approach has three steps. First, we train specialized teachers independently on labeled datasets. We then use the specialized teachers to label an unlabeled dataset to create a multi-task pseudo labeled dataset. Finally, the dataset, which now contains pseudo labels from teacher models trained on different datasets/tasks, is then used to train a student model with multi-task learning. We evaluate the feature representations of the student model on 6 vision tasks including image recognition (classification, detection, segmentation)and 3D geometry estimation (depth and surface normal estimation). MuST is scalable with unlabeled or partially labeled datasets and outperforms both specialized supervised models and self-supervised models when training on large scale datasets. Lastly, we show MuST can improve upon already strong checkpoints trained with billions of examples. The results suggest self-training is a promising direction to aggregate labeled and unlabeled training data for learning general feature representations.

ICCV 2021

References in corpus (7)

• Distilling the Knowledge in a Neural Network
• An Overview of Multi-Task Learning in Deep Neural Networks
• Billion-scale semi-supervised learning for image classification
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
• Self-training Improves Pre-training for Natural Language Understanding
• An Analysis of Pre-Training on Object Detection