The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers

• URL: http://arxiv.org/abs/2512.07331v1
• Date: Mon, 08 Dec 2025 09:18:32 GMT
• Title: The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers
• Abstract summary: Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs)<n>Recent observations suggest ViTs spontaneously manifest a "U-shaped" entropy profile-compressing information in middle layers before expanding it for the final classification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a "U-shaped" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this "Inductive Bottleneck" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DINO-trained ViTs across datasets of varying compositional complexity (UC Merced, Tiny ImageNet, and CIFAR-100), we show that the depth of the bottleneck correlates strongly with the semantic abstraction required by the task. We find that while texture-heavy datasets preserve high-rank representations throughout, object-centric datasets drive the network to dampen high-frequency information in middle layers, effectively "learning" a bottleneck to isolate semantic features.

Related papers

• SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces [91.71563221166417]
  Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost.<n>We propose an efficient neural implicit geometry representation framework with spatially adaptive network depth.
  arXiv  Detail & Related papers  (2026-04-15T14:14:17Z)
• Mechanisms of Non-Monotonic Scaling in Vision Transformers [0.0]
  We identify a consistent three-phase Cliff-au-Climb pattern that governs how representations evolve with depth.<n>We quantify patterns of information mixing with an Information Scrambling Index, and show that in ViT-L the information-task tradeoff emerges roughly 10 layers later than in ViT-B.
  arXiv  Detail & Related papers  (2025-11-26T18:07:14Z)
• MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity [32.532780329341186]
  Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset.<n>Several DFQ methods have been proposed for vision transformer (ViT) architectures, but they fail to achieve efficacy in low-bit settings.<n>We devise MimiQ, a novel DFQ method designed for ViTs that enhances inter-head attention similarity.
  arXiv  Detail & Related papers  (2024-07-29T13:57:40Z)
• Sub-token ViT Embedding via Stochastic Resonance Transformers [51.12001699637727]
  Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. We propose a training-free method inspired by "stochastic resonance" The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization.
  arXiv  Detail & Related papers  (2023-10-06T01:53:27Z)
• Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation [13.056764072568749]
  Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) on smaller datasets. We propose a module called Local InFormation Enhancer (LIFE) that extracts patch-level local information and incorporates it into the embeddings used in the self-attention block of ViTs. Our proposed module is memory and efficient, as well as flexible enough to process auxiliary tokens such as the classification and distillation tokens.
  arXiv  Detail & Related papers  (2023-05-15T11:23:18Z)
• What do Vision Transformers Learn? A Visual Exploration [68.50771218442776]
  Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision. This paper addresses the obstacles to performing visualizations on ViTs and explores the underlying differences between ViTs and CNNs. We also conduct large-scale visualizations on a range of ViT variants, including DeiT, CoaT, ConViT, PiT, Swin, and Twin.
  arXiv  Detail & Related papers  (2022-12-13T16:55:12Z)
• Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets [91.25055890980084]
  There still remains an extreme performance gap between Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) when training from scratch on small datasets. We propose Dynamic Hybrid Vision Transformer (DHVT) as the solution to enhance the two inductive biases. Our DHVT achieves a series of state-of-the-art performance with a lightweight model, 85.68% on CIFAR-100 with 22.8M parameters, 82.3% on ImageNet-1K with 24.0M parameters.
  arXiv  Detail & Related papers  (2022-10-12T06:54:39Z)
• Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning [0.0]
  We study pretraining a Vision Transformer using several state-of-the-art self-supervised methods and assess the quality of the learned representations. Our results show that all methods are effective in learning useful representations and avoiding representational collapse. The encoder pretrained with the temporal order verification task shows the best results across all experiments.
  arXiv  Detail & Related papers  (2022-09-22T10:18:59Z)
• Vision Transformers: From Semantic Segmentation to Dense Prediction [139.15562023284187]
  We explore the global context learning potentials of vision transformers (ViTs) for dense visual prediction. Our motivation is that through learning global context at full receptive field layer by layer, ViTs may capture stronger long-range dependency information. We formulate a family of Hierarchical Local-Global (HLG) Transformers, characterized by local attention within windows and global-attention across windows in a pyramidal architecture.
  arXiv  Detail & Related papers  (2022-07-19T15:49:35Z)
• Do Vision Transformers See Like Convolutional Neural Networks? [45.69780772718875]
  Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. Are they acting like convolutional networks, or learning entirely different visual representations? We find striking differences between the two architectures, such as ViT having more uniform representations across all layers.
  arXiv  Detail & Related papers  (2021-08-19T17:27:03Z)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)

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.