mlsanityData to 7 Oct 2026

ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning

arXiv 2408.14868 ↗First posted 27 Aug 2024cs.CVcited by 2

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen classes to unseen ones, guided by semantic information. To this end, existing works have demonstrated remarkable performance by utilizing global visual features from Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs) for visual-semantic interactions. Due to the limited receptive fields of CNNs and the quadratic complexity of ViTs, however, these visual backbones achieve suboptimal visual-semantic interactions. In this paper, motivated by the visual state space model (i.e., Vision Mamba), which is capable of capturing long-range dependencies and modeling complex visual dynamics, we propose a parameter-efficient ZSL framework called ZeroMamba to advance ZSL. Our ZeroMamba comprises three key components: Semantic-aware Local Projection (SLP), Global Representation Learning (GRL), and Semantic Fusion (SeF). Specifically, SLP integrates semantic embeddings to map visual features to local semantic-related representations, while GRL encourages the model to learn global semantic representations. SeF combines these two semantic representations to enhance the discriminability of semantic features. We incorporate these designs into Vision Mamba, forming an end-to-end ZSL framework. As a result, the learned semantic representations are better suited for classification. Through extensive experiments on four prominent ZSL benchmarks, ZeroMamba demonstrates superior performance, significantly outperforming the state-of-the-art (i.e., CNN-based and ViT-based) methods under both conventional ZSL (CZSL) and generalized ZSL (GZSL) settings. Code is available at: https://anonymous.4open.science/r/ZeroMamba.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 23 of its 39 references that are in the map. First posted on arXiv 27 Aug 2024.

Builds on

23 of 39 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  8. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  9. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  10. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  11. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  12. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
11 more
  1. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  2. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  3. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  4. 2023Improving Zero-Shot Generalization for CLIP with Synthesized Promptscited by 51
  5. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  6. 2023Zero-Shot Learning by Harnessing Adversarial Samplescited by 24
  7. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  8. 2023Image-free Classifier Injection for Zero-Shot Classificationcited by 15
  9. 2023Knowledge Distillation in Vision Transformers: A Critical Reviewcited by 13
  10. 2022Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesiscited by 11
  11. 2024MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilitiescited by 0
  2. 2026Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cuescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning
  2. 2025Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model
  3. 2024RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning
  4. 2023Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
  5. 2022VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
  6. 2024Discriminative Image Generation with Diffusion Models for Zero-Shot Learning
  7. 2023Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
  8. 2024Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification