mlsanityData to 7 Oct 2026

Learning Visual-Semantic Subspace Representations

arXiv 2405.16213 ↗First posted 25 May 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning image representations that capture rich semantic relationships remains a significant challenge. Existing approaches are either contrastive, lacking robust theoretical guarantees, or struggle to effectively represent the partial orders inherent to structured visual-semantic data. In this paper, we introduce a nuclear norm-based loss function, grounded in the same information theoretic principles that have proved effective in self-supervised learning. We present a theoretical characterization of this loss, demonstrating that, in addition to promoting class orthogonality, it encodes the spectral geometry of the data within a subspace lattice. This geometric representation allows us to associate logical propositions with subspaces, ensuring that our learned representations adhere to a predefined symbolic structure.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 52 references that are in the map. First posted on arXiv 25 May 2024.

Builds on

23 of 52 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. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  6. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  7. 2022When and why vision-language models behave like bags-of-words, and what to do about it?cited by 603
  8. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  9. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 160
  10. 2020Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reductioncited by 141
  11. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 128
  12. 2015Order-Embeddings of Images and Languagecited by 112
11 more
  1. 2014Word Representations via Gaussian Embeddingcited by 96
  2. 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
  3. 2020From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clusteringcited by 65
  4. 2018Probabilistic Embedding of Knowledge Graphs with Box Lattice Measurescited by 64
  5. 2017Neural Embeddings of Graphs in Hyperbolic Spacecited by 58
  6. 2024Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negationscited by 45
  7. 2021Hyperbolic Busemann Learning with Ideal Prototypescited by 40
  8. 2017OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learningcited by 37
  9. 2023Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representationscited by 31
  10. 2021Probabilistic Entity Representation Model for Reasoning over Knowledge Graphscited by 28
  11. 2016Quasimetric embeddings and their applicationscited by 3

Built on by

Not cited yet.