Evaluating Contrastive Models for Instance-based Image Retrieval
arXiv:2104.14939 · doi:10.1145/3460426.3463585
Abstract
In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image retrieval, where relevancy is defined in terms of instances of the same object. Through our extensive evaluation, we find that representations from models trained using contrastive methods perform on-par with (and outperforms) a pre-trained supervised baseline trained on the ImageNet labels in retrieval tasks under various configurations. This is remarkable given that the contrastive models require no explicit supervision. Thus, we conclude that these models can be used to bootstrap base models to build more robust image retrieval engines.
arXiv commentAccepted In Proceedings of the 2021 International Conference on Multimedia Retrieval (ICMR 21)
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Improved Baselines with Momentum Contrastive Learning
- Learning deep representations by mutual information estimation and maximization
- Contrastive Representation Learning: A Framework and Review
- Learning Representations by Maximizing Mutual Information Across Views
- Particular object retrieval with integral max-pooling of CNN activations
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Aggregating Deep Convolutional Features for Image Retrieval
- Bags of Local Convolutional Features for Scalable Instance Search