mlsanityData to 14 Oct 2026

ARC: Anchored Representation Clouds for High-Resolution INR Classification

arXiv 2503.15156 ↗First posted 19 Mar 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Implicit neural representations (INRs) encode signals in neural network weights as a memory-efficient representation, decoupling sampling resolution from the associated resource costs. Current INR image classification methods are demonstrated on low-resolution data and are sensitive to image-space transformations. We attribute these issues to the global, fully-connected MLP neural network architecture encoding of current INRs, which lack mechanisms for local representation: MLPs are sensitive to absolute image location and struggle with high-frequency details. We propose ARC: Anchored Representation Clouds, a novel INR architecture that explicitly anchors latent vectors locally in image-space. By introducing spatial structure to the latent vectors, ARC captures local image data which in our testing leads to state-of-the-art implicit image classification of both low- and high-resolution images and increased robustness against image-space translation. Code can be found at https://github.com/JLuij/anchored_representation_clouds.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 56 of its 65 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

56 of 65 references.

References · 56

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  10. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  11. 2018On the Spectral Bias of Neural Networkscited by 1,341
  12. 2016Group Equivariant Convolutional Networkscited by 1,165
38 more
  1. 2020Neural Sparse Voxel Fieldscited by 959
  2. 2020Convolutional Occupancy Networkscited by 761
  3. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  4. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  5. 2021Neural Fields in Visual Computing and Beyondcited by 540
  6. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  7. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  8. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  9. 2021COIN: COmpression with Implicit Neural representationscited by 233
  10. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  11. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  12. 2021Implicit Neural Representations for Image Compressioncited by 162
  13. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  14. 2020In Defense of Grid Features for Visual Question Answeringcited by 155
  15. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  16. 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 135
  17. 2020Predicting Neural Network Accuracy from Weightscited by 110
  18. 2023Equivariant Architectures for Learning in Deep Weight Spacescited by 107
  19. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  20. 2023Permutation Equivariant Neural Functionalscited by 70
  21. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  22. 2020Classifying the classifier: dissecting the weight space of neural networkscited by 65
  23. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  24. 2022On the Symmetries of Deep Learning Models and their Internal Representationscited by 64
  25. 2023Deep Learning on Implicit Neural Representations of Shapescited by 63
  26. 2023Spatial Implicit Neural Representations for Global-Scale Species Mappingcited by 59
  27. 2024Graph Neural Networks for Learning Equivariant Representations of Neural Networkscited by 59
  28. 2023Spatial Functa: Scaling Functa to ImageNet Classification and Generationcited by 57
  29. 2023Neural Functional Transformerscited by 52
  30. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  31. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  32. 2022HyperTime: Implicit Neural Representation for Time Seriescited by 24
  33. 2024Improved Generalization of Weight Space Networks via Augmentationscited by 24
  34. 2024Scale Equivariant Graph Metanetworkscited by 24
  35. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  36. 2024Grounding Continuous Representations in Geometry: Equivariant Neural Fieldscited by 19
  37. 2021Efficient Classification of Very Large Images with Tiny Objectscited by 17
  38. 2022Trading Positional Complexity vs. Deepness in Coordinate Networkscited by 16

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025End-to-End Implicit Neural Representations for Classificationcited by 7
  2. 2025Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spacescited by 1
  3. 2026Is Class Signal Clustered or Routed in Task-Induced Implicit Neural Representation Weight Spaces?cited by 0