VITAL: VIsual Tracking via Adversarial Learning

By Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson W. H. Lau, Ming-Hsuan Yang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

533 citations recorded by the source corpus.

The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existing trackers using deep classification networks is limited by two aspects. First, the positive samples in each frame are highly spatially overlapped, and they fail to capture rich appearance variations. Second, there exists extreme class imbalance between positive and negative samples. This paper presents the VITAL algorithm to address these two problems via adversarial learning. To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes. With the use of adversarial learning, our network identifies the mask that maintains the most robust features of the target objects over a long temporal span. In addition, to handle the issue of class imbalance, we propose a high-order cost sensitive loss to decrease the effect of easy negative samples to facilitate training the classification network. Extensive experiments on benchmark datasets demonstrate that the proposed tracker performs favorably against state-of-the-art approaches.

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

View Paper: https://www.semanticscholar.org/paper/7cbad516a393ca808d6bb30e2b49cc82628af1e5

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

Evolutionary Generative Adversarial Networks (2018, background): “visual tracking [34]–[36], domain adaption [37], hashing coding [38]–[40], and feature learning [41], [42].”
Is First Person Vision Challenging for Object Tracking? (2020, unknown): “We also considered deep siamese networks (SiamFC [8], GOTURN [36], DSLT [52], SiamRPN++ [48], SiamDW [91], UpdateNet [90], SiamFC++ [86], SiamBAN [15], Ocean [92]), trackingby-detection methods (MDNet [62], VITAL [73]), as well as trackers based on target segmentation representations (SiamMask [80],”
SeqTrack: Sequence to Sequence Learning for Visual Object Tracking (2023, methodology): “Prior knowledge, such as window penalty [2,27] and online update [12, 28, 53], has been widely incorporated into existing tracking models and proved effective [7,10,43,55].”
Target-Aware Deep Tracking (2019, methodology): “The VITAL tracker [36] exploits adversarial learning to generate effective samples and addresses class imbalance with a cost-sensitive loss.”
Autoregressive Visual Tracking (2023, background): “Visual object tracking [5, 20, 34, 38, 48, 52] is a foundational objective in the realm of computer vision, whereby the tracker endeavors to estimate the location of an arbitrary target in each video frame, based on its initial state.”
Sphere Generative Adversarial Network Based on Geometric Moment Matching (2019, methodology): “[8], generative adversarial networks (GANs) have attracted much research interest, and they have been used to achieve outstanding performance in a wide range of computer vision applications including in image generation [17, 26], super resolution [14], video prediction [19], style transfer [5, 12, 3”
Siamese Box Adaptive Network for Visual Tracking (2020, methodology): “We evaluate our tracker on the test set consisting of 280 videos with trackers including DiMP [2], ATOM [5], SiamRPN++ [20], C-RPN [10], MDNet [28], VITAL [35], StructSiam [48], DSiam[11], ECO [6].”
STMTrack: Template-free Visual Tracking with Space-time Memory Networks (2021, methodology): “We test our tracker on the testing set of LaSOT [5], and compare it with twelve competitive methods: LTMU [3], DiMP-50 [1], Occean [21], SiamFC++ [18], GlobalTrack [8], SiamCAR [6], ATOM [4], SiamBAN [2], SiamRPN++ [10], UpdateNet [20], ROAM++ [19], and VITAL [16].”
AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization (2020, background): “, deep feature representation [18, 34, 17, 20], reinforcement learning [16], residual learning [35] and adversarial learning [36].”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting ”
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions (2019, background): “GANs for 3D Point Clouds Generation: GANs [13] for 2D image generation tasks have been widely studied with great success [10, 18, 23, 26, 33, 36, 42, 43, 49, 50], but GANs for 3D point cloud generation have rarely been studied in the computer vision field.”
Unveiling the Power of Deep Tracking (2018, methodology): “We compare our method with the following state-of-the-art methods: CCOT [7], ECO [1], TCNN [14], VITAL [36], SA-Siam [37], FlowTrack [38], LSART [39], CREST [16], and Staple [3].”
Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment (2020, methodology): “In addition to image generation tasks, GANs have been introduced to tasks, such as video generation, visual tracking [70], domain adaption [71], hashing coding [72], and”
Probabilistic Regression for Visual Tracking (2020, methodology): “We compare with state-of-the-art trackers DiMP [2], ATOM [5], SiamRPN++ [12], MDNet [14], VITAL [15], and SiamFC [1].”
How Generative Adversarial Networks and Their Variants Work (2017, methodology): “In addition, a GAN was proposed for new applications such as cipher cracking [36] and object tracking [119].”