Learning and aggregating deep local descriptors for instance-level recognition
By Giorgos Tolias, Tomás Jenícek, Ondvrej Chum. 2020
116 citations recorded by the source corpus.
We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image descriptors. At inference, the local descriptors are provided by the activations of internal components of the network. We demonstrate why such an approach learns local descriptors that work well for image similarity estimation with classical efficient match kernel methods. The experimental validation studies the trade-off between performance and memory requirements of the state-of-the-art image search approach based on match kernels. Compared to existing local descriptors, the proposed ones perform better in two instance-level recognition tasks and keep memory requirements lower. We experimentally show that global descriptors are not effective enough at large scale and that local descriptors are essential. We achieve state-of-the-art performance, in some cases even with a backbone network as small as ResNet18.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Jack Sim
- Tobias Weyand
- Andre F. de Araújo
- Bingyi Cao
- Andrew Zisserman
- Ankush Gupta
- Carl Doersch
- Andrea Vedaldi
In Computer Vision and Pattern Recognition
- Andrew Zisserman
- Luc Van Gool
- Dacheng Tao
- Andrea Vedaldi
- Jack Sim
- Trevor Darrell
- Chunhua Shen
- Xiaogang Wang
Citations in the corpus
- CrossTransformers: spatially-aware few-shot transfer (2020, background): “Discriminative parts [4, 9, 22, 34, 42, 83] and visual words [74, 101] have a rich history, and have found applications in deformable-parts models [26], classification [70, 101], and retrieval [12, 84].”
- Google Landmarks Dataset v2 – A Large-Scale Benchmark for Instance-Level Recognition and Retrieval (2020, methodology): “Recent papers [55] have also reported results with a small subset of GLDv2, which we believe is a good direction for making evaluations more feasible when only limited resources are available; using the full dataset should be required, though, to draw more robust conclusions.”