When Does Pruning Benefit Vision Representations?

• URL: http://arxiv.org/abs/2507.01722v3
• Date: Tue, 08 Jul 2025 12:38:05 GMT
• Title: When Does Pruning Benefit Vision Representations?
• Authors: Enrico Cassano, Riccardo Renzulli, Andrea Bragagnolo, Marco Grangetto,
• Abstract summary: Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood.<n>This paper investigates how pruning influences vision models across three key dimensions: (i) interpretability, (ii) unsupervised object discovery, and (iii) alignment with human perception.
• Score: 6.306016476757605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key dimensions: (i) interpretability, (ii) unsupervised object discovery, and (iii) alignment with human perception. We first analyze different vision network architectures to examine how varying sparsity levels affect feature attribution interpretability methods. Additionally, we explore whether pruning promotes more succinct and structured representations, potentially improving unsupervised object discovery by discarding redundant information while preserving essential features. Finally, we assess whether pruning enhances the alignment between model representations and human perception, investigating whether sparser models focus on more discriminative features similarly to humans. Our findings also reveal the presence of sweet spots, where sparse models exhibit higher interpretability, downstream generalization and human alignment. However, these spots highly depend on the network architectures and their size in terms of trainable parameters. Our results suggest a complex interplay between these three dimensions, highlighting the importance of investigating when and how pruning benefits vision representations.

Related papers

• 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)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models [4.089889918897877]
  This study challenges the prevailing assumption that vision-based gait recognition relies primarily on motion patterns. We show through a comparative analysis that removing height information leads to notable performance degradation. We propose a spatial transformer model processing individual poses, disregarding any temporal information, which achieves unreasonably good accuracy.
  arXiv  Detail & Related papers  (2024-02-13T09:33:12Z)
• Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learning [4.124934010794795]
  Self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. We investigate the impact of probabilistic modeling on the information bottleneck, shedding light on a trade-off between compression and preservation of information in both representation and loss space. Our findings suggest that introducing an additional bottleneck in the loss space can significantly enhance the ability to detect out-of-distribution examples.
  arXiv  Detail & Related papers  (2023-10-27T12:01:16Z)
• Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension [0.0]
  We take a first step towards understanding basic geometric properties induced by prompts in Stable Diffusion. We find that choice of prompt has a substantial impact on the intrinsic dimension of representations at both layers of the model. Our evidence suggests that intrinsic dimension could be a useful tool for future studies of the impact of different prompts on text-to-image models.
  arXiv  Detail & Related papers  (2023-02-16T16:22:30Z)
• Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning [98.78136504619539]
  Causal Triplet is a causal representation learning benchmark featuring visually more complex scenes. We show that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts.
  arXiv  Detail & Related papers  (2023-01-12T17:43:38Z)
• Sparse Relational Reasoning with Object-Centric Representations [78.83747601814669]
  We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric representations. We find that increasing sparsity, especially on features, improves the performance of some models and leads to simpler relations.
  arXiv  Detail & Related papers  (2022-07-15T14:57:33Z)
• "Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches [29.048660060344574]
  This work aims to shed light on how different pruning methods alter the network's internal feature representation and the corresponding impact on model performance. We introduce a visual geometric analysis of feature representations to compare and highlight the impact of pruning on model performance and feature representation. The proposed tool provides an environment for in-depth comparison of pruning methods and a comprehensive understanding of how model response to common data corruption.
  arXiv  Detail & Related papers  (2022-06-16T04:44:13Z)
• Desiderata for Representation Learning: A Causal Perspective [104.3711759578494]
  We take a causal perspective on representation learning, formalizing non-spuriousness and efficiency (in supervised representation learning) and disentanglement (in unsupervised representation learning) This yields computable metrics that can be used to assess the degree to which representations satisfy the desiderata of interest and learn non-spurious and disentangled representations from single observational datasets.
  arXiv  Detail & Related papers  (2021-09-08T17:33:54Z)
• Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds [109.0016923028653]
  We learn point cloud representation by bidirectional reasoning between the local structures and the global shape without human supervision. We show that our unsupervised model surpasses the state-of-the-art supervised methods on both synthetic and real-world 3D object classification datasets.
  arXiv  Detail & Related papers  (2020-03-29T08:26:08Z)

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.