Dual-triplet Metric Learning For Unsupervised Domain Adaptation In Video-based Face Recognition

Abstract

The scalability and complexity of deep learning models remains a key issue in many of visual recognition applications like, e.g., video surveillance, where fine tuning with labeled image data from each new camera is required to reduce the domain shift between videos captured from the source domain, e.g., a laboratory setting, and the target domain, i.e, an operational environment. In many video surveillance applications, like face recognition (FR) and person re-identification, a pair-wise matcher is used to assign a query image captured using a video camera to the corresponding reference images in a gallery. The different configurations and operational conditions of video cameras can introduce significant shifts in the pair-wise distance distributions, resulting in degraded recognition performance for new cameras. In this paper, a new deep domain adaptation (DA) method is proposed to adapt the CNN embedding of a Siamese network using unlabeled tracklets captured with a new video camera

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyekladious2020dual

Related papers

• Unique Faces Recognition In Videos (2020)6.77
• Domain Adaptation In Multi-view Embedding For Cross-modal Video Retrieval (2021)0.00
• Robust Character Labeling In Movie Videos: Data Resources And Self-supervised Feature Adaptation (2020)6.34
• Domain Alignment With Triplets (2018)0.00
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58