mlsanityData to 7 Oct 2026

Zero-shot Classification using Hyperdimensional Computing

arXiv 2401.16876 ↗First posted 30 Jan 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Classification based on Zero-shot Learning (ZSL) is the ability of a model to classify inputs into novel classes on which the model has not previously seen any training examples. Providing an auxiliary descriptor in the form of a set of attributes describing the new classes involved in the ZSL-based classification is one of the favored approaches to solving this challenging task. In this work, inspired by Hyperdimensional Computing (HDC), we propose the use of stationary binary codebooks of symbol-like distributed representations inside an attribute encoder to compactly represent a computationally simple end-to-end trainable model, which we name Hyperdimensional Computing Zero-shot Classifier~(HDC-ZSC). It consists of a trainable image encoder, an attribute encoder based on HDC, and a similarity kernel. We show that HDC-ZSC can be used to first perform zero-shot attribute extraction tasks and, can later be repurposed for Zero-shot Classification tasks with minimal architectural changes and minimal model retraining. HDC-ZSC achieves Pareto optimal results with a 63.8% top-1 classification accuracy on the CUB-200 dataset by having only 26.6 million trainable parameters. Compared to two other state-of-the-art non-generative approaches, HDC-ZSC achieves 4.3% and 9.9% better accuracy, while they require more than 1.85x and 1.72x parameters compared to HDC-ZSC, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

29 of 39 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  6. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  7. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  8. 2015Label-Embedding for Image Classificationcited by 164
  9. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  10. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  11. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  12. 2016Latent Embeddings for Zero-shot Classificationcited by 129
17 more
  1. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  2. 2022Constrained Few-shot Class-incremental Learningcited by 93
  3. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  4. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
  5. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  6. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  7. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  8. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  9. 2019Attribute-Aware Attention Model for Fine-grained Representation Learningcited by 22
  10. 2018Hardware Optimizations of Dense Binary Hyperdimensional Computing: Rematerialization of Hypervectors, Binarized Bundling, and Combinational Associative Memorycited by 14
  11. 2022In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memorycited by 9
  12. 2019One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesiscited by 8
  13. 2021A 5 μ W Standard Cell Memory-based Configurable Hyperdimensional Computing Accelerator for Always-on Smart Sensingcited by 6
  14. 2020Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rulescited by 4
  15. 2022A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networkscited by 2
  16. 2018FineTag: Multi-attribute Classification at Fine-grained Level in Imagescited by 1
  17. 2021Compositional Fine-Grained Low-Shot Learningcited by 1

Built on by

Not cited yet.