Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Improving Visual Object Tracking through Visual Prompting

About

Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against distractors is challenging due to the limited discriminative capabilities of prevailing trackers. We present a new visual Prompting mechanism for generic Visual Object Tracking (PiVOT) to address this issue. PiVOT proposes a prompt generation network with the pre-trained foundation model CLIP to automatically generate and refine visual prompts, enabling the transfer of foundation model knowledge for tracking. While CLIP offers broad category-level knowledge, the tracker, trained on instance-specific data, excels at recognizing unique object instances. Thus, PiVOT first compiles a visual prompt highlighting potential target locations. To transfer the knowledge of CLIP to the tracker, PiVOT leverages CLIP to refine the visual prompt based on the similarities between candidate objects and the reference templates across potential targets. Once the visual prompt is refined, it can better highlight potential target locations, thereby reducing irrelevant prompt information. With the proposed prompting mechanism, the tracker can generate improved instance-aware feature maps through the guidance of the visual prompt, thus effectively reducing distractors. The proposed method does not involve CLIP during training, thereby keeping the same training complexity and preserving the generalization capability of the pretrained foundation model. Extensive experiments across multiple benchmarks indicate that PiVOT, using the proposed prompting method can suppress distracting objects and enhance the tracker.

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin• 2024

Related benchmarks

TaskDatasetResultRank
Visual Object TrackingTrackingNet (test)
Normalized Precision (Pnorm)90
460
Visual Object TrackingGOT-10k (test)
Average Overlap76.9
378
Object TrackingLaSoT--
333
Object TrackingTrackingNet--
225
Visual Object TrackingGOT-10k
AO76.9
223
Visual Object TrackingUAV123 (test)--
188
Visual Object TrackingOTB100 (test)--
41
Visual Object TrackingAVisT (test)
AUC62.2
35
Visual Object TrackingLaSOT 42 (test)
Success Rate73.4
34
Visual TrackingAVisT--
33
Showing 10 of 15 rows

Other info

Code

Follow for update