English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Object trackers deployed on low-power devices need to be light-weight,however, most of the current state-of-the-art (SOTA) methods rely on usingcompute-heavy backbones built using CNNs or transformers. Large sizes of suchmodels do not allow their deployment in low-power conditions and designingcompressed variants of large tracking models is of great importance. This paperdemonstrates how highly compressed light-weight object trackers can be designedusing neural architectural pruning of large CNN and transformer based trackers.Further, a comparative study on architectural choices best suited to designlight-weight trackers is provided. A comparison between SOTA trackers usingCNNs, transformers as well as the combination of the two is presented to studytheir stability at various compression ratios. Finally results for extremepruning scenarios going as low as 1% in some cases are shown to study thelimits of network pruning in object tracking. This work provides deeperinsights into designing highly efficient trackers from existing SOTA methods.

On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?