UDON: Universal Dynamic Online distillatioN for generic image representations

• URL: http://arxiv.org/abs/2406.08332v1
• Date: Wed, 12 Jun 2024 15:36:30 GMT
• Title: UDON: Universal Dynamic Online distillatioN for generic image representations
• Authors: Nikolaos-Antonios Ypsilantis, Kaifeng Chen, André Araujo, Ondřej Chum,
• Abstract summary: Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications. Existing methods fail to capture important domain-specific knowledge, while ignoring differences in data distribution across different domains. We introduce a new learning technique, dubbed UDON (Universal Dynamic Online DistillatioN) UDON employs multi-teacher distillation, where each teacher is specialized in one domain, to transfer detailed domain-specific knowledge into the student universal embedding.
• Score: 5.487134463783365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications, where objects and entities from any domain must be identified at large scale. Despite recent advances, existing methods fail to capture important domain-specific knowledge, while also ignoring differences in data distribution across different domains. This leads to a large performance gap between efficient universal solutions and expensive approaches utilising a collection of specialist models, one for each domain. In this work, we make significant strides towards closing this gap, by introducing a new learning technique, dubbed UDON (Universal Dynamic Online DistillatioN). UDON employs multi-teacher distillation, where each teacher is specialized in one domain, to transfer detailed domain-specific knowledge into the student universal embedding. UDON's distillation approach is not only effective, but also very efficient, by sharing most model parameters between the student and all teachers, where all models are jointly trained in an online manner. UDON also comprises a sampling technique which adapts the training process to dynamically allocate batches to domains which are learned slower and require more frequent processing. This boosts significantly the learning of complex domains which are characterised by a large number of classes and long-tail distributions. With comprehensive experiments, we validate each component of UDON, and showcase significant improvements over the state of the art in the recent UnED benchmark. Code: https://github.com/nikosips/UDON .

Related papers

• DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning [20.51179258856028]
  Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data. Most existing FL methods assume that domain labels are provided during training, and their evaluation imposes explicit constraints on the number of domains. We propose Disentangled Prompt Tuning (DiPrompT), a method that tackles the above restrictions by learning adaptive prompts for domain generalization in a distributed manner.
  arXiv  Detail & Related papers  (2024-03-11T15:58:15Z)
• Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data [18.41222232863567]
  We propose a novel end-to-end framework called Universal and joint knowledge distillation (UNI-KD) for cross-domain model compression. In particular, we propose to transfer both the universal feature-level knowledge across source and target domains and the joint logit-level knowledge shared by both domains from the teacher to the student model via an adversarial learning scheme.
  arXiv  Detail & Related papers  (2023-07-07T01:48:02Z)
• Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts [33.21435044949033]
  Most existing methods perform training on multiple source domains using a single model. We propose a novel framework for unsupervised test-time adaptation, which is formulated as a knowledge distillation process.
  arXiv  Detail & Related papers  (2022-10-08T02:28:10Z)
• MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization [55.06956781674986]
  We resort to solving the semi-supervised domain generalization task, where there are a few label information in each source domain. We propose MultiMatch, extending FixMatch to the multi-task learning framework, producing the high-quality pseudo-label for SSDG. A series of experiments validate the effectiveness of the proposed method, and it outperforms the existing semi-supervised methods and the SSDG method on several benchmark DG datasets.
  arXiv  Detail & Related papers  (2022-08-11T14:44:33Z)
• HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression [53.90578309960526]
  Large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. We propose a hierarchical relational knowledge distillation (HRKD) method to capture both hierarchical and domain relational information.
  arXiv  Detail & Related papers  (2021-10-16T11:23:02Z)
• Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting [75.80116276369694]
  In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset. We resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet) It is mainly achieved by proposing the novel Variational Attention(VA) technique for explicitly modeling the attention distributions for different domains.
  arXiv  Detail & Related papers  (2021-08-18T08:06:37Z)
• Multi-Domain Adversarial Feature Generalization for Person Re-Identification [52.835955258959785]
  We propose a multi-dataset feature generalization network (MMFA-AAE) It is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to unseen' camera systems. It also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.
  arXiv  Detail & Related papers  (2020-11-25T08:03:15Z)
• DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations [89.78473564527688]
  This paper shows how to use labeled synthetic dataset and unlabeled real-world dataset to train a universal model. In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets. Experimental results show that the proposed annotation-free method is more or less comparable to the counterpart trained with full human annotations.
  arXiv  Detail & Related papers  (2020-11-24T08:15:53Z)
• Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog [70.79442700890843]
  We propose a novel Dynamic Fusion Network (DF-Net) which automatically exploit the relevance between the target domain and each domain. With little training data, we show its transferability by outperforming prior best model by 13.9% on average.
  arXiv  Detail & Related papers  (2020-04-23T08:17:22Z)

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.