Related papers: Collecting Consistently High Quality Object Tracks…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

In this paper, we propose a self-supervised learning procedure for training a robust multi-object tracking (MOT) model given only unlabeled video. While several self-supervisory learning signals have been proposed in prior work on…

Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2)…

Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional…

For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e.g., unlabeled LiDAR…

Tracking human object interaction from videos is important to understand human behavior from the rapidly growing stream of video data. Previous video-based methods require predefined object templates while single-image-based methods are…

Autonomous driving holds great promise in addressing traffic safety concerns by leveraging artificial intelligence and sensor technology. Multi-Object Tracking plays a critical role in ensuring safer and more efficient navigation through…

In this paper, we explore learning end-to-end deep neural trackers without tracking annotations. This is important as large-scale training data is essential for training deep neural trackers while tracking annotations are expensive to…

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…

Adaptive tracking-by-detection approaches are popular for tracking arbitrary objects. They treat the tracking problem as a classification task and use online learning techniques to update the object model. However, these approaches are…

Labeling datasets for supervised object detection is a dull and time-consuming task. Errors can be easily introduced during annotation and overlooked during review, yielding inaccurate benchmarks and performance degradation of deep neural…

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an…

Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging…

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the…

Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively…

Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation, and 2) the complexity of two-stage approaches. To resolve…

This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where,…

Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in…

The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requires additional…

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…