Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology

• URL: http://arxiv.org/abs/2203.01726v1
• Date: Thu, 3 Mar 2022 14:16:22 GMT
• Title: Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
• Authors: S. Kyathanahally, T. Hardeman, M. Reyes, E. Merz, T. Bulas, F. Pomati, and M. Baity-Jesi
• Abstract summary: We show that ensembles of Data-efficient image Transformers (DeiTs) significantly outperform the previous state of the art (SOTA) On all the data sets we test, we achieve a new SOTA, with a reduction of the error with respect to the previous SOTA ranging from 18.48% to 87.50%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monitoring biodiversity is paramount to manage and protect natural resources, particularly in times of global change. Collecting images of organisms over large temporal or spatial scales is a promising practice to monitor and study biodiversity change of natural ecosystems, providing large amounts of data with minimal interference with the environment. Deep learning models are currently used to automate classification of organisms into taxonomic units. However, imprecision in these classifiers introduce a measurement noise that is difficult to control and can significantly hinder the analysis and interpretation of data. In our study, we show that this limitation can be overcome by ensembles of Data-efficient image Transformers (DeiTs), which significantly outperform the previous state of the art (SOTA). We validate our results on a large number of ecological imaging datasets of diverse origin, and organisms of study ranging from plankton to insects, birds, dog breeds, animals in the wild, and corals. On all the data sets we test, we achieve a new SOTA, with a reduction of the error with respect to the previous SOTA ranging from 18.48% to 87.50%, depending on the data set, and often achieving performances very close to perfect classification. The main reason why ensembles of DeiTs perform better is not due to the single-model performance of DeiTs, but rather to the fact that predictions by independent models have a smaller overlap, and this maximizes the profit gained by ensembling. This positions DeiT ensembles as the best candidate for image classification in biodiversity monitoring.

Related papers

• DivShift: Exploring Domain-Specific Distribution Shift in Volunteer-Collected Biodiversity Datasets [0.0]
  We introduce DivShift North American West Coast (DivShift-NAWC), a curated dataset of almost 8 million iNaturalist plant images. We compare model performance across four known biases and observe that they indeed confound model performance. We suggest practical strategies for curating datasets to train deep learning models for monitoring climate change's impacts on the world's biodiversity.
  arXiv  Detail & Related papers  (2024-10-17T23:56:30Z)
• Deep learning-based ecological analysis of camera trap images is impacted by training data quality and size [11.153016596465593]
  We analyse camera trap data from an African savannah and an Asian sub-tropical dry forest. We compare key ecological metrics derived from expert-generated species identifications with those generated from deep neural networks. Our results show that while model architecture has minimal impact, large amounts of noise and reduced dataset size significantly affect these metrics.
  arXiv  Detail & Related papers  (2024-08-26T15:26:27Z)
• Enhancing Ecological Monitoring with Multi-Objective Optimization: A Novel Dataset and Methodology for Segmentation Algorithms [17.802456388479616]
  We introduce a unique semantic segmentation dataset of 6,096 high-resolution aerial images capturing indigenous and invasive grass species in Bega Valley, New South Wales, Australia. This dataset presents a challenging task due to the overlap and distribution of grass species. The dataset and code will be made publicly available, aiming to drive research in computer vision, machine learning, and ecological studies.
  arXiv  Detail & Related papers  (2024-07-25T18:27:27Z)
• SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data [68.2366021016172]
  We present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird. We also provide a dataset in Kenya representing low-data regimes. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks.
  arXiv  Detail & Related papers  (2023-11-02T02:00:27Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)
• Efficient Unsupervised Learning for Plankton Images [12.447149371717]
  Monitoring plankton populations in situ is fundamental to preserve the aquatic ecosystem. The adoption of machine learning algorithms to classify such data may be affected by the significant cost of manual annotation. We propose an efficient unsupervised learning pipeline to provide accurate classification of plankton microorganisms.
  arXiv  Detail & Related papers  (2022-09-14T15:33:16Z)
• Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms [77.25251419910205]
  Harmful algal blooms (HABs) cause significant fish deaths in aquaculture farms. Currently, the standard method to enumerate harmful algae and other phytoplankton is to manually observe and count them under a microscope. We employ Generative Adversarial Networks (GANs) to generate synthetic images.
  arXiv  Detail & Related papers  (2022-08-03T20:15:55Z)
• Zoo-Tuning: Adaptive Transfer from a Zoo of Models [82.9120546160422]
  Zoo-Tuning learns to adaptively transfer the parameters of pretrained models to the target task. We evaluate our approach on a variety of tasks, including reinforcement learning, image classification, and facial landmark detection.
  arXiv  Detail & Related papers  (2021-06-29T14:09:45Z)
• Dynamic $\beta$-VAEs for quantifying biodiversity by clustering optically recorded insect signals [0.6091702876917281]
  We propose an adaptive variant of the variational autoencoder (VAE) capable of clustering data by phylogenetic groups. We demonstrate the usefulness of the dynamic $beta$-VAE on optically recorded insect signals from regions of southern Scandinavia.
  arXiv  Detail & Related papers  (2021-02-10T16:14:13Z)
• Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples [52.549928980694695]
  In situ hybridization (ISH) gene expression pattern images from the same developmental stage are compared. labeling training data with precise stages is very time-consuming even for biologists. We propose a deep two-step low-shot learning framework to accurately classify ISH images using limited training images.
  arXiv  Detail & Related papers  (2020-10-20T06:06:06Z)
• Automatic image-based identification and biomass estimation of invertebrates [70.08255822611812]
  Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
  arXiv  Detail & Related papers  (2020-02-05T21:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.