LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Not on the map. Why?
Abstract (arXiv)
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field, state-of-the-art (SOTA) trackers often fail when faced with adversarial perturbations in the incoming frames. This can lead to significant robustness and security issues when these trackers are deployed in the real world. To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest. This novel continuous representation enables us to reconstruct incoming frames to maintain semantic and appearance consistency with the object of interest and its clean counterparts. As a result, our proposed method successfully defends against different SOTA adversarial tracking attacks while maintaining high accuracy on clean data. In particular, our method significantly increases tracking accuracy under adversarial attacks with around 90% relative improvement on UAV123, which is even higher than the accuracy on clean data.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 9 Apr 2024.
Builds on
37 of 46 references.
References · 37
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2016Adversarial Machine Learning at Scalecited by 934
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
25 more
- 2022Diffusion Models for Adversarial Purificationcited by 469
- 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
- 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
- 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
- 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 328
- 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
- 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
- 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
- 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
- 2021Local Texture Estimator for Implicit Representation Functioncited by 126
- 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
- 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 124
- 2022Transforming Model Prediction for Trackingcited by 117
- 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
- 2020Efficient Adversarial Attacks for Visual Object Trackingcited by 66
- 2021SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Trackingcited by 38
- 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
- 2020Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noisescited by 32
- 2019Physical Adversarial Textures that Fool Visual Object Trackingcited by 30
- 2020Robust Tracking against Adversarial Attackscited by 28
- 2021IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Trackingcited by 25
- 2021Learning to Adversarially Blur Visual Object Trackingcited by 14
- 2022DIMBA: Discretely Masked Black-Box Attack in Single Object Trackingcited by 11
- 2020Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attackscited by 9
- 2022Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Trackingcited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.