Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex

• URL: http://arxiv.org/abs/2608.12408v1
• Date: Tue, 11 Aug 2026 15:50:58 GMT
• Title: Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex
• Abstract summary: We find that a common result in this setting, that untrained or locally trained networks rival or beat backpropagation at early visual cortex, depends strongly on the resolution at which the network is evaluated.<n>Four candidate mechanisms are tested and none accounts for it: train/eval resolution matching, low-level Gabor and pixel structure, the normalization state of the untrained baseline, and convergence of the pooled descriptor toward a global brightness statistic.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Representational similarity analysis (RSA) is increasingly used to ask which learning rules give convolutional networks brain-like representations. Because biologically plausible rules such as feedback alignment, predictive coding and STDP do not scale, studies that include them train small networks on small images (typically 32x32 CIFAR) and then compare them to brain responses modeled at much higher resolution. We find that a common result in this setting, that untrained or locally trained networks rival or beat backpropagation at early visual cortex, depends strongly on the resolution at which the network is evaluated. The V1 gap between an untrained network and a backpropagation-trained one widens from -0.001 +/- 0.007 at the 32px training resolution to +0.044 +/- 0.006 at 224px, growing monotonically across six resolutions (n=5 seeds). It holds in human fMRI and, directionally, in single-seed macaque electrophysiology, along the training trajectory, and for an ImageNet ResNet-50 and a Swin-Tiny transformer trained at 224px. Four candidate mechanisms are tested and none accounts for it: train/eval resolution matching, low-level Gabor and pixel structure, the normalization state of the untrained baseline, and convergence of the pooled descriptor toward a global brightness statistic; three are excluded by interventions holding the convolutional weights bit-identical. A fifth experiment locates the effect: capping image detail at the training resolution while letting the pooled positions grow 12-fold removes about 90% of it, so the dependence is carried by image detail rather than by pooling. Separately, a single scalar luminance value per image reaches rho = 0.075 against the V1 RDM, essentially matching the untrained network's 0.076, which bounds what this style of comparison can resolve. The one learning effect that holds across resolution is backprop above untrained, at LOC.

Related papers

• RIPE++: Reinforced Keypoint Learning from Positive Pairs Only [10.550765983612086]
  Sparse keypoint extraction and matching underpin core tasks in geometric computer vision.<n>We propose a reward that fully exploits the geometric consistency signal, deriving both reward and penalty from a single positive pair.<n>We show that the same RL objective can be extended to the matching stage by adapting LightGlue, raising AUC@5 on MegaDepth1500 from 56.58 to 59.65.
  arXiv  Detail & Related papers  (2026-08-20T06:37:24Z)
• Experimental Analysis of Neural Network-Based Image Classification on the CIFAR-10 Dataset [0.0]
  An experimental investigation of neural image classification on the CIFAR-10 benchmark is presented through fully connected and convolutional network formulations.<n>The analysis emphasizes the complete learning pipeline: image vectorization, normalization, one-hot class encoding, supervised loss minimization, learning-rate selection, mini-batch training, convolutional feature extraction, max-pooling, and validation-based assessment.
  arXiv  Detail & Related papers  (2026-06-17T00:35:27Z)
• Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules [0.0]
  Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex.<n>We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules.
  arXiv  Detail & Related papers  (2026-05-28T20:39:52Z)
• Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI [0.0]
  We compare four learning rules -- backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP) -- applied to identical convolutional architectures.<n>We find that early visual alignment is primarily architecture-driven, while supervised objectives drive late alignment.
  arXiv  Detail & Related papers  (2026-04-18T06:53:35Z)
• CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition [73.51329037954866]
  We propose a robust global representation method with cross-image correlation awareness for visual place recognition. Our method uses the attention mechanism to correlate multiple images within a batch. Our method outperforms state-of-the-art methods by a large margin with significantly less training time.
  arXiv  Detail & Related papers  (2024-02-29T15:05:11Z)
• Glimpse: Generalized Locality for Scalable and Robust CT [10.657105348034753]
  We introduce Glimpse, a local coordinate-based neural network for computed tomography which reconstructs a pixel value by processing only the measurements associated with the neighborhood of the pixel.<n>Glimpse significantly outperforms successful CNNs on OOD samples, while achieving comparable or better performance on in-distribution test data.<n>Glimpse is fully differentiable and can be used plug-and-play in arbitrary deep learning architectures.
  arXiv  Detail & Related papers  (2024-01-01T17:15:42Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining [68.84339672878066]
  We introduce PyramidCLIP, which constructs an input pyramid with different semantic levels, and aligns visual elements and linguistic elements in the form of hierarchy. Experiments on three downstream tasks, including zero-shot image classification, zero-shot image-text retrieval and image object detection, verify the effectiveness of the proposed PyramidCLIP.
  arXiv  Detail & Related papers  (2022-04-29T13:38:42Z)
• UniFormer: Unifying Convolution and Self-attention for Visual Recognition [69.68907941116127]
  Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. We propose a novel Unified transFormer (UniFormer) which seamlessly integrates the merits of convolution and self-attention in a concise transformer format. Our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification.
  arXiv  Detail & Related papers  (2022-01-24T04:39:39Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• A Lightweight Neural Network for Monocular View Generation with Occlusion Handling [46.74874316127603]
  We present a very lightweight neural network architecture, trained on stereo data pairs, which performs view synthesis from one single image. The work outperforms visually and metric-wise state-of-the-art approaches on the challenging KITTI dataset.
  arXiv  Detail & Related papers  (2020-07-24T15:29:01Z)
• Learning to Learn Parameterized Classification Networks for Scalable Input Images [76.44375136492827]
  Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
  arXiv  Detail & Related papers  (2020-07-13T04:27:25Z)
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation [60.80172153614544]
  Un-trained convolutional neural networks have emerged as highly successful tools for image recovery and restoration. We show that an un-trained convolutional neural network can approximately reconstruct signals and images that are sufficiently structured, from a near minimal number of random measurements.
  arXiv  Detail & Related papers  (2020-05-07T15:57:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.