Adversarial Semi-Supervised Multi-Domain Tracking
- URL: http://arxiv.org/abs/2009.14635v1
- Date: Wed, 30 Sep 2020 12:47:28 GMT
- Title: Adversarial Semi-Supervised Multi-Domain Tracking
- Authors: Kourosh Meshgi, Maryam Sadat Mirzaei
- Abstract summary: In visual tracking, the emerging features in shared layers of a multi-domain tracker are crucial for tracking in unseen videos.
We propose a semi-supervised learning scheme to separate domain-invariant and domain-specific features using adversarial learning.
We build a tracker that performs exceptionally on different types of videos.
- Score: 1.0152838128195465
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Neural networks for multi-domain learning empowers an effective combination
of information from different domains by sharing and co-learning the
parameters. In visual tracking, the emerging features in shared layers of a
multi-domain tracker, trained on various sequences, are crucial for tracking in
unseen videos. Yet, in a fully shared architecture, some of the emerging
features are useful only in a specific domain, reducing the generalization of
the learned feature representation. We propose a semi-supervised learning
scheme to separate domain-invariant and domain-specific features using
adversarial learning, to encourage mutual exclusion between them, and to
leverage self-supervised learning for enhancing the shared features using the
unlabeled reservoir. By employing these features and training dedicated layers
for each sequence, we build a tracker that performs exceptionally on different
types of videos.
Related papers
- Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space [4.871119861180455]
We introduce a two-phase representation learning technique using multi-task learning.
We disentangle the latent space by minimizing the mutual information between the prior and latent space.
We assess the model's efficacy across multiple cybersecurity datasets.
arXiv Detail & Related papers (2023-12-28T17:24:13Z) - Multi-Domain Learning From Insufficient Annotations [26.83058974786833]
Multi-domain learning refers to simultaneously constructing a model or a set of models on datasets collected from different domains.
In this paper, we introduce a novel method called multi-domain contrastive learning to alleviate the impact of insufficient annotations.
Experimental results across five datasets demonstrate that MDCL brings noticeable improvement over various SP models.
arXiv Detail & Related papers (2023-05-04T11:50:19Z) - Exploiting Graph Structured Cross-Domain Representation for Multi-Domain
Recommendation [71.45854187886088]
Multi-domain recommender systems benefit from cross-domain representation learning and positive knowledge transfer.
We use temporal intra- and inter-domain interactions as contextual information for our method called MAGRec.
We perform experiments on publicly available datasets in different scenarios where MAGRec consistently outperforms state-of-the-art methods.
arXiv Detail & Related papers (2023-02-12T19:51:32Z) - Attention Diversification for Domain Generalization [92.02038576148774]
Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features.
When applied to unseen domains, state-of-the-art models are usually prone to errors due to domain shift.
We propose a novel Attention Diversification framework, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated.
arXiv Detail & Related papers (2022-10-09T09:15:21Z) - Unsupervised Domain Generalization by Learning a Bridge Across Domains [78.855606355957]
Unsupervised Domain Generalization (UDG) setup has no training supervision in neither source nor target domains.
Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) - an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains.
We show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets.
arXiv Detail & Related papers (2021-12-04T10:25:45Z) - Multimodal Clustering Networks for Self-supervised Learning from
Unlabeled Videos [69.61522804742427]
This paper proposes a self-supervised training framework that learns a common multimodal embedding space.
We extend the concept of instance-level contrastive learning with a multimodal clustering step to capture semantic similarities across modalities.
The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains.
arXiv Detail & Related papers (2021-04-26T15:55:01Z) - Learning to Combine: Knowledge Aggregation for Multi-Source Domain
Adaptation [56.694330303488435]
We propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework.
In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations.
Our approach outperforms existing methods with a remarkable margin.
arXiv Detail & Related papers (2020-07-17T07:52:44Z) - Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute
Recognition [8.883961218702824]
Co-Attentive Sharing (CAS) module extracts discriminative channels and spatial regions for more effective feature sharing in multi-task learning.
Our module outperforms the conventional sharing units and achieves superior results compared to the state-of-the-art approaches using many metrics.
arXiv Detail & Related papers (2020-04-07T07:24:22Z) - Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings [76.85673049332428]
Learned joint representations of images and text form the backbone of several important cross-domain tasks such as image captioning.
We propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately.
We demonstrate the effectiveness of our model on diverse tasks, including image captioning and text-to-image synthesis.
arXiv Detail & Related papers (2020-02-16T19:49:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.