Inducing Stronger Object Representations in Deep Visual Trackers
Fully convolutional deep correlation networks are integral components of state-of- the-art approaches to single object visual tracking. It is commonly assumed that these networks perform tracking by detection by matching features of the object instance with features of the entire frame. Strong architectural priors and conditioning on the object representation is thought to encourage this tracking strategy. Despite these strong priors, we show that deep trackers often default to “tracking- by-saliency” detection – without relying on the object instance representation. Our analysis shows that despite being a useful prior, salience detection can prevent the emergence of more robust tracking strategies in deep networks. This leads us to introduce an auxiliary detection task that encourages more discriminative object representations that improve tracking performance.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSaliency DetectionVisual TrackingSimilar Papers 제목 키워드 기반
Hedged Deep Tracking
In recent years, several methods have been developed to utilize hierarchical features learned from a deep convolutional neural network (CNN) for visual tracking. However, as the features from a certain CNN layer characte…
Visual TrackingAn Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers
Visual object tracking is the problem of predicting a target object's state in a video. Generally, bounding-boxes have been used to represent states, and a surge of effort has been spent by the community to produce effic…
Object TrackingSegmentationVisual Object TrackingAn Analysis of Object Representations in Deep Visual Trackers
Fully convolutional deep correlation networks are integral components of state-of the-art approaches to single object visual tracking. It is commonly assumed that these networks perform tracking by detection by matching …
ObjectSaliency DetectionVisual TrackingTracking Holistic Object Representations
Recent advances in visual tracking are based on siamese feature extractors and template matching. For this category of trackers, latest research focuses on better feature embeddings and similarity measures. In this work,…
DiversityObjectTemplate MatchingVisual Object Tracking+1F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives
Multi-object tracking (MOT) aims to build moving trajectories for number-agnostic objects. Modern multi-object trackers commonly follow the tracking-by-detection strategy. Therefore, fooling detectors can be an effec…
Adversarial AttackMulti-Object TrackingObjectObject Tracking