Compact Network Training for Person ReID

Lawen, Hussam; Ben-Cohen, Avi; Protter, Matan; Friedman, Itamar; Zelnik-Manor, Lihi

doi:10.1145/3372278.3390686

Cited by 12 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [30] calculate the similarity of the input images in multiple levels. Reference [31] emphasized the use of small-sized network usage accelerates the exploration of architecture and training modifications. Reference [32] proposed a method based on Neural Architecture Search to automatically search for an effective CNN specialized for ReID, which alleviates the tedious task of manually designing compact networks.…”

Section: B Fast-reidmentioning

confidence: 99%

Regularizing Binary Neural Networks via Ensembling for Efficient Person Re-Identification

Serbetci

Akgül

2023

IEEE Access

View full text Add to dashboard Cite

This study aims to leverage Binary Neural Networks (BNN) to learn binary hash codes for efficient person re-identification (ReID). BNNs, which use binary weights and activations, show promise in speeding up the inference time in deep models. However, BNNs typically suffer from performance degradation mainly due to the discontinuity of the binarization operation. Proxy functions have been proposed to calculate the gradients in the backward propagation, but they lead to the gradient mismatch problem. In this study, we propose to address the gradient mismatch problem by designing a multi-branch ensemble model consisting of many weak hash code learners. Specifically, our design aggregates the gradients from multiple branches, which allows a better approximation of the gradients and regularizes the network. Our model adds little computational cost to the baseline BNN since a vast amount of network parameters are shared between the weak learners. Combining the efficiency of the BNNs and hash code learning, we obtain an effective ensemble model which is efficient both in feature extraction and ranking phases. Our experiments demonstrate that the proposed model outperforms a single BNN by more than %20 using nearly the same amount of floating point operations. Moreover, the proposed model outperforms a conventional ensemble of BNN by more than %7 while being nearly 10x and 2x more efficient in terms of CPU consumption and memory footprint, respectively. We explore the performance of BNNs for efficient person ReID as one of the first systems available in the literature. Moreover, we adopt the proposed ensemble model for further validation of the image classification task and observe that our method effectively regularizes BNNs, providing robustness to hyperparameter selection and producing more consistent results under different settings.

show abstract

Section: B Fast-reidmentioning

confidence: 99%