SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1511.07247 · 2015

NetVLAD: CNN architecture for weakly supervised place recognition

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ChienYiChi/kaggle-panda-challenge pwc_unofficial 0 of 9
uzh-rpg/netvlad_tf_open pwc_unofficial 0 of 3
FunctionStatusWhere it lives
accuracy Not yet run ChienYiChi/kaggle-panda-challenge/src/utils.py
code served (permissive licence) · get_code("e193c34cf5c21621")
blue_ratio_selection Not yet run ChienYiChi/kaggle-panda-challenge/src/dataset.py
code served (permissive licence) · get_code("dc26c333e39e8ca9")
compute_weights Not yet run ChienYiChi/kaggle-panda-challenge/src/generate_weights.py
code served (permissive licence) · get_code("d40e6d73305e43d0")
crop_white Not yet run ChienYiChi/kaggle-panda-challenge/src/preprocess.py
code served (permissive licence) · get_code("d9a827e75b532949")
evaluate Not yet run uzh-rpg/netvlad_tf_open/python/netvlad_tf/precision_recall.py
code served (permissive licence) · get_code("3e2532b6c170f972")
get_tiles Not yet run ChienYiChi/kaggle-panda-challenge/src/dataset.py
code served (permissive licence) · get_code("aa3e63d35834e2eb")
get_tiles_brs Not yet run ChienYiChi/kaggle-panda-challenge/src/dataset.py
code served (permissive licence) · get_code("4f6eccb6a67664d3")
matconvnetNormalize Not yet run uzh-rpg/netvlad_tf_open/python/netvlad_tf/layers.py
code served (permissive licence) · get_code("0fe927e3be8d314c")
name_to_tile Not yet run ChienYiChi/kaggle-panda-challenge/src/generate_weights.py
code served (permissive licence) · get_code("135081edae587c1d")
netVLAD Not yet run uzh-rpg/netvlad_tf_open/python/netvlad_tf/layers.py
code served (permissive licence) · get_code("1bfe629b56c533b1")
quadratic_weighted_kappa Not yet run ChienYiChi/kaggle-panda-challenge/src/engine.py
code served (permissive licence) · get_code("374f0d897ab43c7e")
setup_logger Not yet run ChienYiChi/kaggle-panda-challenge/src/utils.py
code served (permissive licence) · get_code("f7ee730a2131702b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state-of-the-art compact image representations on standard image retrieval benchmarks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1511.07247")
get_code_for_paper("1511.07247")
have("1511.07247")

Connect an agent — have() is free.