ON DESIGNING LIGHT-WEIGHT OBJECT TRACKERS THROUGH NETWORK PRUNING: USE CNNS OR TRANSFORMERS?

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 using compute-heavy backbones built using CNNs or transformers. Large sizes of such models do not allow their deployment in low-power condi- tions and designing compressed variants of large tracking models is of great importance. This paper demonstrates how highly compressed light-weight object trackers can be designed using neural architectural pruning of large CNN and transformer based trackers. Further, a comparative study on architectural choices best suited to design light- weight trackers is provided. A fair comparison between SOTA trackers using CNNs, transformers as well as the combination of the two is presented to study their stabil- ity at various compression ratios. Finally results for ex- treme pruning scenarios going as low as 1% in some cases are shown to study the limits of network pruning in object tracking. This work provides deeper insights into design- ing highly efficient trackers from existing SOTA methods.