Distilling Channels for Efficient Deep Tracking

doi:10.1109/TIP.2019.2950508

Return

Distilling Channels for Efficient Deep Tracking

2020-01-01

PRE

DOI：10.1109/TIP.2019.2950508

Original

Original request for help

Save

Abstract

En 中文

Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep networks employed are usually trained to extract rich knowledge from massive data used in object classification and so they are capable to represent generic objects very well. However, these networks are too complex to represent a specific moving object, leading to poor generalization as well as high computational and memory costs. This paper presents a novel and general framework termed channel distillation to facilitate deep trackers. To validate the effectiveness of channel distillation, we take discriminative correlation filter (DCF) and ECO for example. We demonstrate that an integrated formulation can turn feature compression, response map generation, and model update into a unified energy minimization problem to adaptively select informative feature channels that improve the efficacy of tracking moving objects on the fly. Channel distillation can accurately extract good channels, alleviating the influence of noisy channels and generally reducing the number of channels, as well as adaptively generalizing to different channels and networks. The resulting deep tracker is accurate, fast, and has low memory requirements. Extensive experimental evaluations on popular benchmarks clearly demonstrate the effectiveness and generalizability of our framework.

Keywords:

Image coding

Visualization

Correlation

Feature extraction

Adaptation models

Benchmark testing

Minimization

Visual tracking

deep tracking

channel distillation

CNNs

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.