Duality-Gated Mutual Condition Network for RGBT Tracking
This work provides an incremental improvement for RGBT tracking, specifically benefiting applications that rely on robust tracking across varying modality qualities.
This paper addresses the underutilization of low-quality modalities in RGBT tracking by proposing a duality-gated mutual condition network. The network effectively enhances target representations across modalities and includes a resampling strategy for sudden camera motion, achieving favorable performance against state-of-the-art algorithms on four RGBT tracking benchmarks.
Low-quality modalities contain not only a lot of noisy information but also some discriminative features in RGBT tracking. However, the potentials of low-quality modalities are not well explored in existing RGBT tracking algorithms. In this work, we propose a novel duality-gated mutual condition network to fully exploit the discriminative information of all modalities while suppressing the effects of data noise. In specific, we design a mutual condition module, which takes the discriminative information of a modality as the condition to guide feature learning of target appearance in another modality. Such module can effectively enhance target representations of all modalities even in the presence of low-quality modalities. To improve the quality of conditions and further reduce data noise, we propose a duality-gated mechanism and integrate it into the mutual condition module. To deal with the tracking failure caused by sudden camera motion, which often occurs in RGBT tracking, we design a resampling strategy based on optical flow algorithms. It does not increase much computational cost since we perform optical flow calculation only when the model prediction is unreliable and then execute resampling when the sudden camera motion is detected. Extensive experiments on four RGBT tracking benchmark datasets show that our method performs favorably against the state-of-the-art tracking algorithms