Distributed Zero-Shot Learning for Visual Recognition
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 56 of its 95 references that are in the map. First posted on arXiv 11 Nov 2025.
Builds on
56 of 95 references.
References · 56
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2021Model-Contrastive Federated Learningcited by 766
- 2018Local SGD Converges Fast and Communicates Littlecited by 605
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
- 2019Fair Resource Allocation in Federated Learningcited by 394
- 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
38 more
- 2015Label-Embedding for Image Classificationcited by 165
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2020Federated Visual Classification with Real-World Data Distributioncited by 128
- 2019Zero-Shot Knowledge Distillation in Deep Networkscited by 121
- 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
- 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
- 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
- 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
- 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
- 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
- 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
- 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
- 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
- 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
- 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
- 2020A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansioncited by 31
- 2021Domain Adaptive Semantic Segmentation without Source Datacited by 30
- 2020Attribute Propagation Network for Graph Zero-shot Learningcited by 29
- 2020Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patchescited by 27
- 2023Zero-Shot Learning by Harnessing Adversarial Samplescited by 24
- 2019CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Languagecited by 23
- 2017Zero-Shot Recognition using Dual Visual-Semantic Mapping Pathscited by 20
- 2024Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baselinecited by 19
- 2024PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentationcited by 14
- 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
- 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12
- 2024Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospectscited by 12
- 2024Snap and Diagnose: An Advanced Multimodal Retrieval System for Identifying Plant Diseases in the Wildcited by 12
- 2025Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routingcited by 12
- 2021Disentangling Semantic-to-visual Confusion for Zero-shot Learningcited by 11
- 2023Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Errorcited by 10
- 2024FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuningcited by 10
- 2021Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learningcited by 8
- 2024Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learningcited by 8
- 2025On the Discrimination and Consistency for Exemplar-Free Class Incremental Learningcited by 8
- 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
- 2025SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learningcited by 6
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.