Understanding Visual Feature Reliance through the Lens of Complexity

• URL: http://arxiv.org/abs/2407.06076v2
• Date: Mon, 28 Oct 2024 11:15:06 GMT
• Title: Understanding Visual Feature Reliance through the Lens of Complexity
• Authors: Thomas Fel, Louis Bethune, Andrew Kyle Lampinen, Thomas Serre, Katherine Hermann,
• Abstract summary: We introduce a new metric for quantifying feature complexity, based on $mathscrV$-information. We analyze the complexities of 10,000 features, represented as directions in the penultimate layer, that were extracted from a standard ImageNet-trained vision model.
• Score: 14.282243225622093
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus on understanding the complexity of the myriad features that models learn. In this work, we introduce a new metric for quantifying feature complexity, based on $\mathscr{V}$-information and capturing whether a feature requires complex computational transformations to be extracted. Using this $\mathscr{V}$-information metric, we analyze the complexities of 10,000 features, represented as directions in the penultimate layer, that were extracted from a standard ImageNet-trained vision model. Our study addresses four key questions: First, we ask what features look like as a function of complexity and find a spectrum of simple to complex features present within the model. Second, we ask when features are learned during training. We find that simpler features dominate early in training, and more complex features emerge gradually. Third, we investigate where within the network simple and complex features flow, and find that simpler features tend to bypass the visual hierarchy via residual connections. Fourth, we explore the connection between features complexity and their importance in driving the networks decision. We find that complex features tend to be less important. Surprisingly, important features become accessible at earlier layers during training, like a sedimentation process, allowing the model to build upon these foundational elements.

Related papers

• Learned feature representations are biased by complexity, learning order, position, and more [4.529707672004383]
  We explore surprising dissociations between representation and computation. We train various deep learning architectures to compute multiple abstract features about their inputs. We find that their learned feature representations are systematically biased towards representing some features more strongly than others.
  arXiv  Detail & Related papers  (2024-05-09T15:34:15Z)
• How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model [4.215221129670858]
  We show that by introducing sparsity to generative hierarchical models of data, the task acquires insensitivity to spatial transformations that are discrete versions of smooth transformations. We quantify how the sample complexity of CNNs learning the SRHM depends on both the sparsity and hierarchical structure of the task.
  arXiv  Detail & Related papers  (2024-04-16T17:01:27Z)
• Simplicity in Complexity : Explaining Visual Complexity using Deep Segmentation Models [6.324765782436764]
  We propose to model complexity using segment-based representations of images. We find that complexity is well-explained by a simple linear model with these two features across six diverse image-sets.
  arXiv  Detail & Related papers  (2024-03-05T17:21:31Z)
• Feature Network Methods in Machine Learning and Applications [0.0]
  A machine learning (ML) feature network is a graph that connects ML features in learning tasks based on their similarity. We provide an example of a deep tree-structured feature network, where hierarchical connections are formed through feature clustering and feed-forward learning.
  arXiv  Detail & Related papers  (2024-01-10T01:57:12Z)
• Rotating Features for Object Discovery [74.1465486264609]
  We present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations. Together, these advancements enable us to scale distributed object-centric representations from simple toy to real-world data.
  arXiv  Detail & Related papers  (2023-06-01T12:16:26Z)
• Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks [66.76034024335833]
  We investigate why diverse/ complex features are learned by the backbone, and their brittleness is due to the linear classification head relying primarily on the simplest features. We propose Feature Reconstruction Regularizer (FRR) to ensure that the learned features can be reconstructed back from the logits. We demonstrate up to 15% gains in OOD accuracy on the recently introduced semi-synthetic datasets with extreme distribution shifts.
  arXiv  Detail & Related papers  (2022-10-04T04:01:15Z)
• Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information [77.19830787312743]
  In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand. We introduce a new problem setting for reinforcement learning, the Exogenous Decision Process (ExoMDP), in which the state space admits an (unknown) factorization into a small controllable component and a large irrelevant component. We provide a new algorithm, ExoRL, which learns a near-optimal policy with sample complexity in the size of the endogenous component.
  arXiv  Detail & Related papers  (2022-06-09T05:19:32Z)
• Feature Forgetting in Continual Representation Learning [48.89340526235304]
  representations do not suffer from "catastrophic forgetting" even in plain continual learning, but little further fact is known about its characteristics. We devise a protocol for evaluating representation in continual learning, and then use it to present an overview of the basic trends of continual representation learning. To study the feature forgetting problem, we create a synthetic dataset to identify and visualize the prevalence of feature forgetting in neural networks.
  arXiv  Detail & Related papers  (2022-05-26T13:38:56Z)
• Dist2Cycle: A Simplicial Neural Network for Homology Localization [66.15805004725809]
  Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations. We propose a graph convolutional model for learning functions parametrized by the $k$-homological features of simplicial complexes.
  arXiv  Detail & Related papers  (2021-10-28T14:59:41Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• What shapes feature representations? Exploring datasets, architectures, and training [14.794135558227682]
  In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. These questions are important for understanding the basis of models' decisions. We study these questions using synthetic datasets in which the task-relevance of input features can be controlled directly.
  arXiv  Detail & Related papers  (2020-06-22T17:02:25Z)

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.