Deep Heterogeneous Multi-Task Metric Learning for Visual Recognition and Retrieval
Shikang Gan, Yong Luo, Yonggang Wen, Tongliang Liu, Han Hu
Abstract
How to estimate the distance between data instances is a fundamental problem in many artificial intelligence algorithms, and critical in diverse multimedia applications. A major challenge in the estimation is how to find an appropriate distance function when labeled data are insufficient for a certain task. Multi-task metric learning (MTML) is able to alleviate such data deficiency issue by learning distance metrics for multiple tasks together and sharing information between the different tasks. Recently, heterogeneous MTML (HMTML) has attracted much attention since it can handle multiple tasks with varied data representations. A major drawback of the current HMTML approaches is that only linear transformations are learned to connect different domains. This is suboptimal since the correlations between different domains may be very complex and highly nonlinear. To overcome this drawback, we propose a deep heterogeneous MTML (DHMTML) method, in which a nonlinear mapping is learned for each task by using a deep neural network. The correlations of different domains are exploited by sharing some parameters at the top layers of different networks. More importantly, the auto-encoder scheme and the adversarial learning mechanism are integrated and incorporated to help exploit the feature correlations in and between different tasks and the specific properties are preserved by learning additional task-specific layers together with the common layers. Experiments demonstrated that the proposed method outperforms single-task deep metric learning algorithms and other HMTML approaches consistently on several benchmark datasets.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
its abstract · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Related papers
- Semi-supervised Online Multi-Task Metric Learning for Visual Recognition and RetrievalYangxi Li, Han Hu, Jin Li, Yong Luo et al.ACM MM 2020 · 3 citations
- Dual Adversarial Co-Learning for Multi-Domain Text ClassificationYuan Wu, Yuhong GuoAAAI 2020 · 26 citations
- T-MDML: Triplet-based Multiple Distance Metric Learning for Multi-Instance Multi-Label Classification with Label CorrelationDongyeon Kim, Yejin Kan, Gangman YiAAAI 2025 · 1 citation
- Meta Distant Transfer Learning for Pre-trained Language ModelsChengyu Wang, Haojie Pan, Minghui Qiu, Jun Huang et al.EMNLP 2021 · 3 citations
- Improving Multi-Task Generalization via Regularizing Spurious CorrelationZiniu Hu, Zhe Zhao, Xinyang Yi, Tiansheng Yao et al.NeurIPS 2022 · 46 citations
