MixFormer: End-to-End Tracking with Iterative Mixed Attention

🤖 Plain-English Summary

Tracking often uses a multistage pipeline of feature extraction, target information integration, and bounding box estimation. We also perform in-depth ablation studies to demonstrate the effectiveness of simultaneous feature extraction and information integration.

🔑 Key Findings

• To simplify this pipeline and unify the process of feature extraction and target information integration, we present a compact tracking framework, termed as MixFormer, built upon transformers.
• Our core design is to utilize the flexibility of attention operations, and propose a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration.
• This synchronous modeling scheme allows to extract target-specific discriminative features and perform extensive communication between target and search area.

🔗 Related Resources