# ARC: Anchored Representation Clouds for High-Resolution INR Classification Source: [ARC: Anchored Representation Clouds for High-Resolution INR Classification]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:49:55.154Z Authors: Joost Luijmes, Alexander Gielisse, Roman Knyazhitskiy, Jan van Gemert Published: 2025-03-19T12:24:29.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()