Domain-Aware Continual Zero-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes. DIN continually learns a global shared network for domain-invariant and task-invariant features, and per-task private networks for task-specific features. Furthermore, we enhance the dual network with class-wise learnable prompts to improve class-level text representation, thereby improving zero-shot prediction of future unseen classes. To evaluate DACZSL, we introduce two benchmarks, DomainNet-CZSL and iWildCam-CZSL. Our results show that DIN significantly outperforms existing baselines by over 5% in harmonic accuracy and over 1% in backward transfer and achieves a new SoTA.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 53 of its 77 references that are in the map. First posted on arXiv 24 Dec 2021.
Builds on
53 of 77 references.
References · 53
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2015Domain-Adversarial Training of Neural Networkscited by 3,044
- 2021Learning to Prompt for Vision-Language Modelscited by 2,281
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
38 more
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
- 2017Gradient Episodic Memory for Continual Learningcited by 1,898
- 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
- 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
- 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
- 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
- 2018Efficient Lifelong Learning with A-GEMcited by 1,058
- 2020In Search of Lost Domain Generalizationcited by 1,054
- 2019How Can We Know What Language Models Know?cited by 959
- 2021Robust fine-tuning of zero-shot modelscited by 797
- 2019Large Scale Incremental Learningcited by 732
- 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
- 2018Recognition in Terra Incognitacited by 658
- 2018End-to-End Incremental Learningcited by 597
- 2018Progress & Compress: A scalable framework for continual learningcited by 520
- 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
- 2016Domain Separation Networkscited by 320
- 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
- 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
- 2018Task-Free Continual Learningcited by 221
- 2020Representation Learning via Invariant Causal Mechanismscited by 199
- 2021How Many Data Points is a Prompt Worth?cited by 198
- 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
- 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 161
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
- 2020Adversarial Continual Learningcited by 142
- 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
- 2019Overcoming Catastrophic Forgetting with Unlabeled Data in the Wildcited by 111
- 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 102
- 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
- 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
- 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
- 2021The iWildCam 2021 Competition Datasetcited by 77
- 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
- 2020Towards Recognizing Unseen Categories in Unseen Domainscited by 56
- 2020Frustratingly Simple Domain Generalization via Image Stylizationcited by 43
- 2019Creativity Inspired Zero-Shot Learningcited by 27
- 2020Generalized Continual Zero-Shot Learningcited by 7
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.
3 papers.