From images in the wild to video-informed image classification

Image classifiers work effectively when applied on structured images, yet they often fail when applied on images with very high visual complexity. This paper describes experiments applying state-of-the-art object classifiers toward a unique set of ‘images in the wild’ with high visual complexity collected on the island of Bali. The text describes differences between actual images in the wild and images from Imagenet, and then discusses a novel approach combining informational cues particular to video with an ensemble of imperfect classifiers in order to improve classification results on video sourced images of plants in the wild.

• Publication year

  2021

• Venue

  International Conference on Machine Learning and Applications

• Publication date

  2021-09-24

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/ICMLA52953.2021.00109arXiv 2109.12040
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A generalizable and accessible approach to machine learning with global satellite imagery

  2020cited by this paper
• Machine Learning in Ethnobotany

  2020cited by this paper
• Artificial Intelligence and Conservation

  2019cited by this paper
• Image-based classification of plant genus and family for trained and untrained plant species

  2019cited by this paper
• AI empowers conservation biology

  2019cited by this paper
• The role of artificial intelligence in achieving the Sustainable Development Goals

  2019cited by this paper
• Overview of LifeCLEF Plant Identification Task 2019: diving into Data Deficient Tropical Countries

  2019influential reference
• Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection

  2019cited by this paper
• and s

  2019cited by this paper
• Plant Recognition by Inception Networks with Test-time Class Prior Estimation

  2018cited by this paper
• Overview of LifeCLEF 2018: A Large-Scale Evaluation of Species Identification and Recommendation Algorithms in the Era of AI

  2018cited by this paper
• Deep Reinforcement Learning of Region Proposal Networks for Object Detection

  2018cited by this paper
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  2015cited by this paper
• Improving Image Classification with Location Context

  2015cited by this paper
• Media Images and the Social Construction of Reality

  1992cited by this paper

• Visualization of Tree Species Identification Using Mask RCNNs for Tropical Forests in Malaysia

  2022cites this paper