Dimensions underlying the representational alignment of deep neural networks with humans

• URL: http://arxiv.org/abs/2406.19087v2
• Date: Mon, 27 Jan 2025 13:19:27 GMT
• Title: Dimensions underlying the representational alignment of deep neural networks with humans
• Authors: Florian P. Mahner, Lukas Muttenthaler, Umut Güçlü, Martin N. Hebart,
• Abstract summary: We propose a generic framework to compare human and AI representations, based on identifying latent representational dimensions.<n>Applying this framework to humans and a deep neural network (DNN) model of natural images revealed a low-dimensional DNN embedding of both visual and semantic dimensions.<n>While in-silico experiments showed seemingly consistent interpretability of DNN dimensions, a direct comparison between human and DNN representations revealed substantial differences in how they process images.
• Score: 3.1668470116181817
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Determining the similarities and differences between humans and artificial intelligence (AI) is an important goal both in computational cognitive neuroscience and machine learning, promising a deeper understanding of human cognition and safer, more reliable AI systems. Much previous work comparing representations in humans and AI has relied on global, scalar measures to quantify their alignment. However, without explicit hypotheses, these measures only inform us about the degree of alignment, not the factors that determine it. To address this challenge, we propose a generic framework to compare human and AI representations, based on identifying latent representational dimensions underlying the same behavior in both domains. Applying this framework to humans and a deep neural network (DNN) model of natural images revealed a low-dimensional DNN embedding of both visual and semantic dimensions. In contrast to humans, DNNs exhibited a clear dominance of visual over semantic properties, indicating divergent strategies for representing images. While in-silico experiments showed seemingly consistent interpretability of DNN dimensions, a direct comparison between human and DNN representations revealed substantial differences in how they process images. By making representations directly comparable, our results reveal important challenges for representational alignment and offer a means for improving their comparability.

Related papers

• A Meaningful Perturbation Metric for Evaluating Explainability Methods [55.09730499143998]
  We introduce a novel approach, which harnesses image generation models to perform targeted perturbation. Specifically, we focus on inpainting only the high-relevance pixels of an input image to modify the model's predictions while preserving image fidelity. This is in contrast to existing approaches, which often produce out-of-distribution modifications, leading to unreliable results.
  arXiv  Detail & Related papers  (2025-04-09T11:46:41Z)
• When Does Perceptual Alignment Benefit Vision Representations? [76.32336818860965]
  We investigate how aligning vision model representations to human perceptual judgments impacts their usability. We find that aligning models to perceptual judgments yields representations that improve upon the original backbones across many downstream tasks. Our results suggest that injecting an inductive bias about human perceptual knowledge into vision models can contribute to better representations.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Divergences in Color Perception between Deep Neural Networks and Humans [3.0315685825606633]
  We develop experiments for evaluating the perceptual coherence of color embeddings in deep neural networks (DNNs) We assess how well these algorithms predict human color similarity judgments collected via an online survey. We compare DNN performance against an interpretable and cognitively plausible model of color perception based on wavelet decomposition.
  arXiv  Detail & Related papers  (2023-09-11T20:26:40Z)
• Evaluating alignment between humans and neural network representations in image-based learning tasks [5.657101730705275]
  We tested how well the representations of $86$ pretrained neural network models mapped to human learning trajectories. We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation. In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks.
  arXiv  Detail & Related papers  (2023-06-15T08:18:29Z)
• Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features [119.45320143101381]
  Graph convolutional networks (GCN) leverage topology-driven graph convolutional operations to combine information across the graph for inference tasks. We have studied GCNs with covariance matrices as graphs in the form of coVariance neural networks (VNNs) VNNs inherit the scale-free data processing architecture from GCNs and here, we show that VNNs exhibit transferability of performance over datasets whose covariance matrices converge to a limit object.
  arXiv  Detail & Related papers  (2023-05-02T22:15:54Z)
• Harmonizing the object recognition strategies of deep neural networks with humans [10.495114898741205]
  We show that state-of-the-art deep neural networks (DNNs) are becoming less aligned with humans as their accuracy improves. Our work represents the first demonstration that the scaling laws that are guiding the design of DNNs today have also produced worse models of human vision.
  arXiv  Detail & Related papers  (2022-11-08T20:03:49Z)
• Human alignment of neural network representations [28.32452075196472]
  We investigate the factors that affect the alignment between the representations learned by neural networks and human mental representations inferred from behavioral responses. We find that model scale and architecture have essentially no effect on the alignment with human behavioral responses. We find that some human concepts such as food and animals are well-represented by neural networks whereas others such as royal or sports-related objects are not.
  arXiv  Detail & Related papers  (2022-11-02T15:23:16Z)
• Predicting Brain Age using Transferable coVariance Neural Networks [119.45320143101381]
  We have recently studied covariance neural networks (VNNs) that operate on sample covariance matrices. In this paper, we demonstrate the utility of VNNs in inferring brain age using cortical thickness data. Our results show that VNNs exhibit multi-scale and multi-site transferability for inferring brain age In the context of brain age in Alzheimer's disease (AD), our experiments show that i) VNN outputs are interpretable as brain age predicted using VNNs is significantly elevated for AD with respect to healthy subjects.
  arXiv  Detail & Related papers  (2022-10-28T18:58:34Z)
• Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks [61.60177890353585]
  Deep convolutional neural networks (CNNs) have been shown to provide excellent models for its functional analogue in the brain, the ventral stream in visual cortex. Here we consider some prominent statistical patterns that are known to exist in the internal representations of either CNNs or the visual cortex. We show that CNNs and visual cortex share a similarly tight relationship between dimensionality expansion/reduction of object representations and reformatting of image information.
  arXiv  Detail & Related papers  (2022-05-27T08:06:40Z)
• WenLan 2.0: Make AI Imagine via a Multimodal Foundation Model [74.4875156387271]
  We develop a novel foundation model pre-trained with huge multimodal (visual and textual) data. We show that state-of-the-art results can be obtained on a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2021-10-27T12:25:21Z)
• Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study [7.222232547612573]
  Deep convolutional neural networks (DCNNs) and the ventral visual pathway share vast architectural and functional similarities. We demonstrate a comparison of human observers (N = 45) and three feedforward DCNNs through eye tracking and saliency maps. A DCNN with biologically plausible receptive field sizes called vNet reveals higher agreement with human viewing behavior as contrasted with a standard ResNet architecture.
  arXiv  Detail & Related papers  (2021-07-30T23:32:05Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks [82.54695985117783]
  We investigate the suitability of state-of-the-art deep learning architectures for continuous emotion recognition using long video sequences captured in-the-wild. We have developed and evaluated convolutional recurrent neural networks combining 2D-CNNs and long short term-memory units, and inflated 3D-CNN models, which are built by inflating the weights of a pre-trained 2D-CNN model during fine-tuning.
  arXiv  Detail & Related papers  (2020-11-18T13:42:05Z)
• Fooling the primate brain with minimal, targeted image manipulation [67.78919304747498]
  We propose an array of methods for creating minimal, targeted image perturbations that lead to changes in both neuronal activity and perception as reflected in behavior. Our work shares the same goal with adversarial attack, namely the manipulation of images with minimal, targeted noise that leads ANN models to misclassify the images.
  arXiv  Detail & Related papers  (2020-11-11T08:30:54Z)
• DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
  We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
  arXiv  Detail & Related papers  (2020-08-26T17:59:40Z)
• Seeing eye-to-eye? A comparison of object recognition performance in humans and deep convolutional neural networks under image manipulation [0.0]
  This study aims towards a behavioral comparison of visual core object recognition performance between humans and feedforward neural networks. Analyses of accuracy revealed that humans not only outperform DCNNs on all conditions, but also display significantly greater robustness towards shape and most notably color alterations.
  arXiv  Detail & Related papers  (2020-07-13T10:26:30Z)

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.