Related papers: Efficient coding along the visual hierarchy

Efficient coding along the visual hierarchy

URL: http://arxiv.org/abs/2605.19155v1
Date: Mon, 18 May 2026 22:20:17 GMT
Title: Efficient coding along the visual hierarchy
Abstract summary: We show that efficient coding can build a hierarchy of human-aligned visual features from limited data.<n>A hybrid learning procedure that combines efficient coding with supervised fine-tuning yields better brain alignment in low-data settings.<n>These findings suggest that efficient coding may shape representations across the entire visual hierarchy.
Score: 0.764671395172401
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Biological visual systems learn from limited experience, unlike deep learning models that rely on millions of training images. What learning principles make this possible? We tested whether efficient coding, the idea that neural representations capture the statistical structure of natural inputs, can build a hierarchy of human-aligned visual features from limited data. We developed an unsupervised learning procedure in which each layer of a deep network compresses its inputs onto the dominant modes of variation in natural images, using only local statistics and no labels, tasks, or backpropagation. This unsupervised procedure yields features that progress from edges and colors to textures and shapes. The features of this deep efficient coding model are readily recognized by human observers and are predictive of image-evoked fMRI responses in human visual cortex. Furthermore, a hybrid learning procedure that combines efficient coding with supervised fine-tuning yields better brain alignment in low-data settings and more rapid category learning. These findings suggest that efficient coding may shape representations across the entire visual hierarchy and help explain the data efficiency of biological vision.

Related papers

In Pursuit of Pixel Supervision for Visual Pre-training [60.63095313440605]
"Pixio" is an enhanced masked autoencoder (MAE) trained on 2B web-crawled images with a self-curation strategy with minimal human curation.<n>Pixio performs competitively across a wide range of downstream tasks in the wild, including monocular depth estimation, feed-forward 3D reconstruction, semantic segmentation, and robot learning.<n>Our results suggest that pixel-space self-supervised learning can serve as a promising alternative and a complement to latent-space approaches.
arXiv Detail & Related papers (2025-12-17T18:59:58Z)
Adaptive Decoding via Hierarchical Neural Information Gradients in Mouse Visual Tasks [7.199942082447265]
hierarchically deep neural networks (DNNs) have played a significant role as tools for mining the core features of complex data.<n>We propose a method for studying the adaptive topological decoding between brain regions, called the Adaptive Topological Vision Transformer, or AT-ViT.<n>In numerous experiments, the results reveal the importance of the proposed method in hierarchical networks in the visual tasks.
arXiv Detail & Related papers (2025-10-10T15:00:59Z)
From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images [1.77513002450736]
A bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction.<n>Our results show that the encoder stage consistently exhibits the highest correlation with human perceptual judgments on image distortion.
arXiv Detail & Related papers (2025-08-14T08:37:30Z)
L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement [12.524893323311108]
We show that image perturbations can enhance the ability of humans to accurately report the ground truth class.<n>We propose to augment visual learning in humans in a way that improves human categorization accuracy at test time.
arXiv Detail & Related papers (2024-12-12T23:57:01Z)
Convolution goes higher-order: a biologically inspired mechanism empowers image classification [0.8999666725996975]
We propose a novel approach to image classification inspired by complex nonlinear biological visual processing.<n>Our model incorporates a Volterra-like expansion of the convolution operator, capturing multiplicative interactions.<n>Our work bridges neuroscience and deep learning, offering a path towards more effective, biologically inspired computer vision models.
arXiv Detail & Related papers (2024-12-09T18:33:09Z)
MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning [48.97640824497327]
We propose a novel framework leveraging domain-specific medical knowledge as guiding signals to integrate language information into the visual domain through image-text contrastive learning. Our model includes global contrastive learning with our designed divergence encoder, local token-knowledge-patch alignment contrastive learning, and knowledge-guided category-level contrastive learning with expert knowledge. Notably, MLIP surpasses state-of-the-art methods even with limited annotated data, highlighting the potential of multimodal pre-training in advancing medical representation learning.
arXiv Detail & Related papers (2024-02-03T05:48:50Z)
Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
arXiv Detail & Related papers (2023-03-17T18:00:27Z)
Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images [79.07468367923619]
We develop convolutional neural generative coding (Conv-NGC) We implement a flexible neurobiologically-motivated algorithm that progressively refines latent state maps. We study the effectiveness of our brain-inspired neural system on the tasks of reconstruction and image denoising.
arXiv Detail & Related papers (2022-11-22T06:42:41Z)
Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
arXiv Detail & Related papers (2022-02-01T17:11:13Z)
Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition [77.95361323613147]
Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset. In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness. Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
arXiv Detail & Related papers (2021-03-31T08:15:17Z)
Self supervised contrastive learning for digital histopathology [0.0]
We use a contrastive self-supervised learning method called SimCLR that achieved state-of-the-art results on natural-scene images. We find that combining multiple multi-organ datasets with different types of staining and resolution properties improves the quality of the learned features. Linear classifiers trained on top of the learned features show that networks pretrained on digital histopathology datasets perform better than ImageNet pretrained networks.
arXiv Detail & Related papers (2020-11-27T19:18:45Z)

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