Towards Zero-Shot Camera Trap Image Categorization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vyskočil, Jiří, Picek, Lukas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912074709336064
author Vyskočil, Jiří
Picek, Lukas
author_facet Vyskočil, Jiří
Picek, Lukas
contents This paper describes the search for an alternative approach to the automatic categorization of camera trap images. First, we benchmark state-of-the-art classifiers using a single model for all images. Next, we evaluate methods combining MegaDetector with one or more classifiers and Segment Anything to assess their impact on reducing location-specific overfitting. Last, we propose and test two approaches using large language and foundational models, such as DINOv2, BioCLIP, BLIP, and ChatGPT, in a zero-shot scenario. Evaluation carried out on two publicly available datasets (WCT from New Zealand, CCT20 from the Southwestern US) and a private dataset (CEF from Central Europe) revealed that combining MegaDetector with two separate classifiers achieves the highest accuracy. This approach reduced the relative error of a single BEiTV2 classifier by approximately 42\% on CCT20, 48\% on CEF, and 75\% on WCT. Besides, as the background is removed, the error in terms of accuracy in new locations is reduced to half. The proposed zero-shot pipeline based on DINOv2 and FAISS achieved competitive results (1.0\% and 4.7\% smaller on CCT20, and CEF, respectively), which highlights the potential of zero-shot approaches for camera trap image categorization.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Zero-Shot Camera Trap Image Categorization
Vyskočil, Jiří
Picek, Lukas
Computer Vision and Pattern Recognition
This paper describes the search for an alternative approach to the automatic categorization of camera trap images. First, we benchmark state-of-the-art classifiers using a single model for all images. Next, we evaluate methods combining MegaDetector with one or more classifiers and Segment Anything to assess their impact on reducing location-specific overfitting. Last, we propose and test two approaches using large language and foundational models, such as DINOv2, BioCLIP, BLIP, and ChatGPT, in a zero-shot scenario. Evaluation carried out on two publicly available datasets (WCT from New Zealand, CCT20 from the Southwestern US) and a private dataset (CEF from Central Europe) revealed that combining MegaDetector with two separate classifiers achieves the highest accuracy. This approach reduced the relative error of a single BEiTV2 classifier by approximately 42\% on CCT20, 48\% on CEF, and 75\% on WCT. Besides, as the background is removed, the error in terms of accuracy in new locations is reduced to half. The proposed zero-shot pipeline based on DINOv2 and FAISS achieved competitive results (1.0\% and 4.7\% smaller on CCT20, and CEF, respectively), which highlights the potential of zero-shot approaches for camera trap image categorization.
title Towards Zero-Shot Camera Trap Image Categorization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.12769