LifeCLEF 2016: Multimedia Life Species Identification Challenges

Abstract

Abstract. Using multimedia identification tools is considered as one of the most promising solutions to help bridge the taxonomic gap and build accurate knowledge of the identity, the geographic distribution and the evolution of living species. Large and structured communities of nature observers (e.g., iSpot, Xeno-canto, Tela Botanica, etc.) as well as big monitoring equipment have actually started to produce outstanding collections of multimedia records. Unfortunately, the performance of the state-of-the-art analysis techniques on such data is still not well understood and is far from reaching real world requirements. The LifeCLEF lab proposes to evaluate these challenges around 3 tasks related to multimedia information retrieval and fine-grained classification problems in 3 domains. Each task is based on large volumes of real-world data and the measured challenges are defined in collaboration with biologists and environmental stakeholders to reflect realistic usage scenarios. For each task, we report the methodology, the data sets as well as the results and the main outcomes.

Data-Efficient Classification of Birdcall through Convolutional Neural Networks Transfer Learning

“…Currently, supervised deep learning methods have gained popularity for automatic call classification in acoustic recordings. In the LifeCLEF Bird (Audio) Identification Task 2016/2017 algorithm benchmarking competition, the top algorithms were a variation of fully supervised deep learning CNN architecture [35], [36]. However, CNN models are heavily reliant on a large number of labelled samples, using experts to obtain such a large number of labelled records in acoustics is an expensive and time-consuming endeavour.…”

Automated Identification of Herbarium Specimens at Different Taxonomic Levels

“…PlantCLEF is the largest and best known plant identification challenge [6]. It has helped to create bigger datasets each year as well as allowed participants to gradually improve the techniques (mostly deep learning based models) to achieve better accuracy.…”

LifeCLEF 2017 Lab Overview: Multimedia Species Identification Challenges

“…The evaluation metrics are the precision, the counting score (CS), and the normalized counting score (NCS). More information about these metrics and the whole set up of the subtask can be found in the LifeCLEF 2016 overview [26].…”

“…The metric used to evaluate each run is the Average Precision. More information about this metric and the whole set up of the subtask can be found in the LifeCLEF 2016 overview [26]. P@5 of the two participant teams (HITSZ and SIATMMLAB) that submitted three runs each.…”