Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers

By Eunbyung Park, Alexander C. Berg. 2018

175 citations recorded by the source corpus.

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learning, the resulting networks train significantly faster. We demonstrate this approach on top of the high performance tracking approaches: tracking-by-detection based MDNet and the correlation based CREST. Experimental results on standard benchmarks, OTB2015 and VOT2016, show that our meta-learned versions of both trackers improve speed, accuracy, and robustness.

Subfields: Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Risk, Reliability and Quality

Citations in the corpus

Target-Aware Deep Tracking (2019, methodology): “the correlation filters based trackers, such as SRDCF [9], Staple [1], MCPF [48], CCOT [10], ECO [7], BACF [17], DRT [38], STRCF [22], and MCCT-H [43]; the non-realtime deep trackers such as MDNet [29], CREST [35], LSART [37], FlowT [52], DSLT [25], MetaSDNet [30], VITAL [36], and DAT [31]; and the ”
Learning the Model Update for Siamese Trackers (2019, methodology): “The meta-tracker of [33] extends the initialization of the target model in the first frame by a pre-trained approach, but still need a linear update in on-line tracking.”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, background): “Tracker [80]; meta-learning based tracker MetaTracker [61]; attentive tracker DAT [79]; and other convolutional neural networks based approaches MDNet [60], GOTURN [54],”
Learning Discriminative Model Prediction for Tracking (2019, methodology): “[31] develop a meta-learning framework employing an initial target independent model, which is then refined using gradient descent with learned step-lengths.”
Ocean: Object-aware Anchor-free Tracking (2020, methodology): “There are 9 anchor-based Siamese framework based methods (SiamFC [1], GradNet [24], DSiam [11], MemDTC [46], SiamRPN [22], C-RPN [9], SiamMASK [43], SiamRPN++ [21] and SiamRCNN [39]), 8 discriminative correlation filter based methods (CFNet [38], ECO [5], STRCF [23], LADCF [45], UDT [42], STN [37], ”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “Tracker [182], CRVFL [183], VTCNN [184], BGBDT [185], GFS-DCF [186], GradNet [187], MLT [188], UpdateNet [189], CGACD [190], CSA [191], D3S [192], OSAA [193], PrDiMP [194], RLS [195], ROAM [196], SiamAttn [197], SiamBAN [198], SiamCAR [199], SiamRCNN [200], TMAML [201], FGTrack [202], DHT [203], MLC”