Revisiting IM2GPS in the Deep Learning Era
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Image geolocalization, inferring the geographic location of an image, is a challenging computer vision problem with many potential applications. The recent state-of-the-art approach to this problem is a deep image classification approach in which the world is spatially divided into cells and a deep network is trained to predict the correct cell for a given image. We propose to combine this approach with the original Im2GPS approach in which a query image is matched against a database of geotagged images and the location is inferred from the retrieved set. We estimate the geographic location of a query image by applying kernel density estimation to the locations of its nearest neighbors in the reference database. Interestingly, we find that the best features for our retrieval task are derived from networks trained with classification loss even though we do not use a classification approach at test time. Training with classification loss outperforms several deep feature learning methods (e.g. Siamese networks with contrastive of triplet loss) more typical for retrieval applications. Our simple approach achieves state-of-the-art geolocalization accuracy while also requiring significantly less training data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267 · cited 1×
“Image retrieval using learned, deep representations is useful to a wide range of tasks such as product ranking [4, 12], sketch based image retrieval [25], face recognition [31, 26], cross-view localization [18, 37, 34] and scene retrieval [33, 2, 23, 8].”
BackgroundDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search
Jegou, H., Douze, M., & Schmid, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_24 · Cited by 1,901
Deep Image Retrieval: Learning Global Representations for Image Search
Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_15 · Cited by 787 · cited 4×
“We are studying image retrieval geolocalization which has overlap with instance-level scene retrieval [33, 2, 23, 7]; Since this line of work mostly focuses on instance-level matching, benchmarks designed for this task consist of popular scenes or landmarks [21, 22, 12] and similarity between…”
BackgroundMethodInfluentialParticular object retrieval with integral max-pooling of CNN activations
Tolias, G., Sicre, R., & Jégou, H. (2015) · arXiv · doi:10.48550/arxiv.1511.05879 · Cited by 744 · cited 2×
“We are studying image retrieval geolocalization which has overlap with instance-level scene retrieval [33, 2, 23, 7]; Since this line of work mostly focuses on instance-level matching, benchmarks designed for this task consist of popular scenes or landmarks [21, 22, 12] and similarity between…”
BackgroundMethodYFCC100M: The New Data in Multimedia Research
Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2015) · arXiv · doi:10.48550/arxiv.1503.01817 · Cited by 69
Cited by
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Hu, S., Feng, M., Nguyen, R. M. H., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00758 · Cited by 394
Geography-Aware Self-Supervised Learning
Ayush, K., Uzkent, B., Meng, C., Tanmay, K., Burke, M., Lobell, D., & Ermon, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01002 · Cited by 288
Presence-Only Geographical Priors for Fine-Grained Image Classification
Aodha, O. M., Cole, E., & Perona, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00969 · Cited by 149
Metadata
- Authors
- Vo, N., Jacobs, N., & Hays, J.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2640-2649
- OpenAlex
- W2964213180
- Cited by
- 122
- References
- 7
- FWCI
- 3.88
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.