Dog nose print matching with dual global descriptor based on Contrastive Learning

Abstract

Recent studies in biometric-based identification tasks have shown that deep learning methods can achieve better performance. These methods generally extract the global features as descriptor to represent the original image. Nonetheless, it does not perform well for biometric identification under fine-grained tasks. The main reason is that the single image descriptor contains insufficient information to represent image. In this paper, we present a dual global descriptor model, which combines multiple global descriptors to exploit multi level image features. Moreover, we utilize a contrastive loss to enlarge the distance between image representations of confusing classes. The proposed framework achieves the top2 on the

Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks

“…Zhou et al used EfficientNetV2 for fine-tuning the EfficientNet-B7 pretrained model to create a machine that extracts features from whole-body portraits and generates Lego brick models [ 40 ]. This approach was also used for dog nose print matching [ 41 ] and prediction of the energy consumption of 3D printing processes [ 42 ].…”