Corpus ID: 237091126

Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring

@article{Pantazis2021FocusOT,
  title={Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring},
  author={Omiros Pantazis and Gabriel J. Brostow and Kate Jones and Oisin Mac Aodha},
  journal={ArXiv},
  year={2021},
  volume={abs/2108.06435}
}
We address the problem of learning self-supervised representations from unlabeled image collections. Unlike existing approaches that attempt to learn useful features by maximizing similarity between augmented versions of each input image or by speculatively picking negative samples, we instead also make use of the natural variation that occurs in image collections that are captured using static monitoring cameras. To achieve this, we exploit readily available context data that encodes… Expand

References

SHOWING 1-10 OF 63 REFERENCES
Automated identification of animal species in camera trap images
TLDR
An automated species identification method for wildlife pictures captured by remote camera traps that uses improved sparse coding spatial pyramid matching (ScSPM), which extracts dense SIFT descriptor and cell-structured LBP as the local features and generates global feature via weighted sparse coding and max pooling using multi-scale pyramid kernel. Expand
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
TLDR
The ability to automatically, accurately, and inexpensively collect such data, which could help catalyze the transformation of many fields of ecology, wildlife biology, zoology, conservation biology, and animal behavior into “big data” sciences is investigated. Expand
Geography-Aware Self-Supervised Learning
TLDR
This paper proposes novel training methods that exploit the spatiotemporal structure of remote sensing data to close the gap between contrastive and supervised learning on image classification, object detection and semantic segmentation for remote sensing and other geo-tagged image datasets. Expand
Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna
TLDR
This work deployed 225 camera traps across Serengeti National Park, Tanzania, to evaluate spatial and temporal inter-species dynamics and classified the images via the citizen-science website www.snapshotsereNGeti.org, yielding a final classification for each image and a measure of agreement among individual answers. Expand
The iNaturalist Species Classification and Detection Dataset
TLDR
The iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals, is presented, which features visually similar species, captured in a wide variety of situations, from all over the world. Expand
Efficient Pipeline for Camera Trap Image Review
TLDR
A pipeline is proposed that takes advantage of a pre-trained general animal detector and a smaller set of labeled images to train a classification model that can efficiently achieve accurate results in a new region. Expand
Presence-Only Geographical Priors for Fine-Grained Image Classification
TLDR
An efficient spatio-temporal prior is proposed, that when conditioned on a geographical location and time, estimates the probability that a given object category occurs at that location. Expand
Scaling and Benchmarking Self-Supervised Visual Representation Learning
TLDR
It is shown that by scaling on various axes (including data size and problem 'hardness'), one can largely match or even exceed the performance of supervised pre-training on a variety of tasks such as object detection, surface normal estimation and visual navigation using reinforcement learning. Expand
Local Aggregation for Unsupervised Learning of Visual Embeddings
TLDR
This work describes a method that trains an embedding function to maximize a metric of local aggregation, causing similar data instances to move together in the embedding space, while allowing dissimilar instances to separate. Expand
Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds
TLDR
The problem of large-scale fine-grained visual categorization is addressed, describing new methods used to produce an online field guide to 500 North American bird species and state-of-the-art recognition performance is shown on a new, large dataset made publicly available. Expand
...
1
2
3
4
5
...