Similarity Learning Networks for Animal Individual Re-Identification - Beyond the Capabilities of a Human Observer

@article{Schneider2020SimilarityLN,
  title={Similarity Learning Networks for Animal Individual Re-Identification - Beyond the Capabilities of a Human Observer},
  author={Stefan Schneider and Graham W. Taylor and Stefan S. Linquist and Stefan C. Kremer},
  journal={2020 IEEE Winter Applications of Computer Vision Workshops (WACVW)},
  year={2020},
  pages={44-52}
}
Deep learning has become the standard methodology to approach computer vision tasks when large amounts of labeled data are available. One area where traditional deep learning approaches fail to perform is one-shot learning tasks where a model must correctly classify a new category after seeing only one example. One such domain is animal re-identification, an application of computer vision which can be used globally as a method to automate species population estimates from camera trap images… Expand
Comparing Class-Aware and Pairwise Loss Functions for Deep Metric Learning in Wildlife Re-Identification
TLDR
It is demonstrated that no single neural network architecture combined with a loss function is best suited for all datasets, although VGG-11 may be the most robust first choice. Expand
Unique Animal Identification using Deep Transfer Learning For Data Fusion in Siamese Networks
TLDR
It is argued that uniquely identifying individuals such as nyala who actively try to disguise themselves in their environments require improved few-shot learning techniques and perhaps more data than the current open dataset to stimulate this area of research. Expand
Revisiting animal photo-identification using deep metric learning and network analysis
TLDR
This work developed an end-to-end pipeline to retrieve a comprehensive set of re-identified giraffes from about 4, 000 raw photographs, and quantified the performance of deep metric learning to retrieve the identity of known individuals and detect unknown individuals never seen in the previous years of monitoring. Expand
Revisiting giraffe photo-identification using deep learning and network analysis
An increasing number of research programs rely on photographic capture-recapture (vs. direct marking) of individuals to study distribution and demography within animal populations.Expand
Deep Learning Methods for Multi-Species Animal Re-identification and Tracking - a Survey
TLDR
The applicability of existing animal re-identification techniques for fully automated individual animal tracking in a cross-camera setup is explored and common trends in re-Identification methods are presented, lists a few challenges in the domain and recommends possible solutions. Expand
Animal reidentification using restricted set classification
TLDR
This work applies Restricted Set Classification (RSC) for classifying multiple animals simultaneously from the same image using a convolutional neural network as the individual classifier and demonstrates that RSC is significantly better than applying just the CNN, as it eliminates duplicate labels in the sameimage and improves the overall classification accuracy. Expand
Automated Identification of Individuals in Wildlife Population Using Siamese Neural Networks
Similarity learning coupled with semi-hard pair mining has been applied successfully in human individual identification using images of faces. This approach is coupled with innovative training dataExpand
Automated facial recognition for wildlife that lack unique markings: A deep learning approach for brown bears
TLDR
The open‐source application BearID and its annotated source code provide a replicable methodology for applying deep learning methods of facial recognition applicable to many other species that lack distinguishing markings, and could facilitate fine‐scale behavioral research such as individual spatiotemporal activity patterns. Expand
Wildlife Action Recognition using Deep Learning
Action recognition is the task of identifying the action(s) performed in a video. Till date most of the action recognition systems are human-centric. In this work, we propose to perform actionExpand
Three critical factors affecting automated image species recognition performance for camera traps
TLDR
The capabilities of deep learning systems trained on camera trap images using modestly sized training data are tested, performance when considering unseen background locations is compared, and the gradient of lower bound performance is quantified to provide a guideline of data requirements in correspondence to performance expectations. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 50 REFERENCES
Individual Common Dolphin Identification Via Metric Embedding Learning
TLDR
It is shown that this compact representation of fin images in a Euclidean embedding can be successfully learnt from a fairly small training set and still generalise well to out-of-sample identities (completely new dolphin individuals), with top-1 and top-5 test set (37 individuals) accuracy. Expand
Automatically identifying wild animals in camera trap images with deep learning
TLDR
This paper uses the existing human-labeled images from the Snapshot Serengeti dataset to train deep convolutional neural networks for identifying 48 species in 3.2 million images taken from Tanzania's Serengenti National Park, and trains neural networks that automatically identify animals with over 92% accuracy. 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
Rethinking the Inception Architecture for Computer Vision
TLDR
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. Expand
Scalable Person Re-identification: A Benchmark
TLDR
A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset. Expand
In Defense of the Triplet Loss for Person Re-Identification
TLDR
It is shown that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin. Expand
Deep Learning Object Detection Methods for Ecological Camera Trap Data
TLDR
This work demonstrates the capabilities of two deep learning object detection classifiers, Faster R-CNN and YOLO v2.0, to identify, quantify, and localize animal species within camera trap images using the Reconyx Camera Trap and the self-labeled Gold Standard Snapshot Serengeti data sets. Expand
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Expand
An Animal Detection Pipeline for Identification
TLDR
The end result of the proposed pipeline is a collection of novel annotations of interest with species and view-point labels, which could be fed as the focused input data into an appearance-based animal identification system. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
...
1
2
3
4
5
...