WILDLABS logoWildlabs.net : The conservation technology network

WILDLABS logoWildlabs.net : The conservation technology network

article / 11 January 2024

New method for improving shape awareness in deep learning

In this paper, we report new polynomial type architectures, that we show improve shape awareness in image recognition applications, including in conditions such as blur and fog, making things potentially useful for camera trap surveys. The experiments in the paper do not test with camera traps directly however, and broadly evaluated on public benchmarks in object recognition.

Groups

This paper won the Best Paper Award at the Deep Learning Meets Geometric Computing (DLGC) workshop held in conjunction with IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023.

Attached Files
Paper

Add the first post in this thread.

Want to share your own conservation tech experiences and expertise with our growing global community? Login or register to start posting!