Learning Test-time Augmentation For Content-based Image Retrieval

Abstract

Off-the-shelf convolutional neural network features achieve outstanding results in many image retrieval tasks. However, their invariance to target data is pre-defined by the network architecture and training data. Existing image retrieval approaches require fine-tuning or modification of pre-trained networks to adapt to variations unique to the target data. In contrast, our method enhances the invariance of off-the-shelf features by aggregating features extracted from images augmented at test-time, with augmentations guided by a policy learned through reinforcement learning. The learned policy assigns different magnitudes and weights to the selected transformations, which are selected from a list of image transformations. Policies are evaluated using a metric learning protocol to learn the optimal policy. The model converges quickly and the cost of each policy iteration is minimal as we propose an off-line caching technique to greatly reduce the computational cost of extracting feature

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keytursun2020learning

Related papers

• A Review Of Image Retrieval Techniques: Data Augmentation And Adversarial Learning Approaches (2024)0.00
• Feature Re-learning With Data Augmentation For Video Relevance Prediction (2020)6.34
• A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
• Retrieval Augmentation For Deep Neural Networks (2021)5.84
• Augnet: End-to-end Unsupervised Visual Representation Learning With Image Augmentation (2021)3.96
• Contrastive Learning With Stronger Augmentations (2021)19.61
• Improving Image Recognition By Retrieving From Web-scale Image-text Data (2023)9.41
• Training Vision Transformers For Image Retrieval (2021)0.00