# DCFNet: Discriminant Correlation Filters Network for Visual Tracking

arXiv: https://arxiv.org/abs/1704.04057 · HTML: https://mlsanity.com/paper/1704.04057/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2017.

## Built on by (most cited first, 11 of 11)

- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [3D Siamese Transformer Network for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2207.11995/) (2022)
- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [Global Instance Tracking: Locating Target More Like Humans](https://mlsanity.com/paper/2202.13073/) (2022)
- [Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking](https://mlsanity.com/paper/2507.07483/) (2025)
- [Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review](https://mlsanity.com/paper/2401.11790/) (2024)
- [Open-World Drone Active Tracking with Goal-Centered Rewards](https://mlsanity.com/paper/2412.00744/) (2024)
- [Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking](https://mlsanity.com/paper/2107.02984/) (2021)
- [Learning Online for Unified Segmentation and Tracking Models](https://mlsanity.com/paper/2111.06994/) (2021)
- [Context-aware Visual Tracking with Joint Meta-updating](https://mlsanity.com/paper/2204.01513/) (2022)
- [Self-Supervised RGB-T Tracking with Cross-Input Consistency](https://mlsanity.com/paper/2301.11274/) (2023)

## Abstract (arXiv)

Discriminant Correlation Filters (DCF) based methods now become a kind of dominant approach to online object tracking. The features used in these methods, however, are either based on hand-crafted features like HoGs, or convolutional features trained independently from other tasks like image classification. In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously. Specifically, we treat DCF as a special correlation filter layer added in a Siamese network, and carefully derive the backpropagation through it by defining the network output as the probability heatmap of object location. Since the derivation is still carried out in Fourier frequency domain, the efficiency property of DCF is preserved. This enables our tracker to run at more than 60 FPS during test time, while achieving a significant accuracy gain compared with KCF using HoGs. Extensive evaluations on OTB-2013, OTB-2015, and VOT2015 benchmarks demonstrate that the proposed DCFNet tracker is competitive with several state-of-the-art trackers, while being more compact and much faster.