Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal continuity provided by videos. We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker. It enables us to learn not only from videos labeled with complete tracks, but also unlabeled or partially labeled videos. We implement this learning objective in a unified form following the spirit of constrastive loss. Experiments on multiple object tracking datasets demonstrate that our method can effectively learning discriminative appearance embeddings in a semi-supervised fashion and outperform state of the art methods on representative benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple Object TrackingObjectObject TrackingRepresentation LearningSimilar Papers 제목 키워드 기반
Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNC…
Contrastive LearningSemi-supervised Contrastive Learning with Similarity Co-calibration
Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-kn…
Contrastive LearningFew-Shot LearningSelf-Supervised LearningSemi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level featu…
Contrastive LearningDomain AdaptationRepresentation LearningSegmentation+3Rethinking Weak Supervision in Helping Contrastive Learning
Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noi…
Contrastive LearningDenoisingWeakly-supervised LearningFBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation
Medical image segmentation of gadolinium enhancement magnetic resonance imaging (GE MRI) is an important task in clinical applications. However, manual annotation is time-consuming and requires specialized expertise. Sem…
Contrastive LearningImage SegmentationMedical Image SegmentationSegmentation+1