# Intriguing Properties of Dynamic Sampling Networks

arXiv: https://arxiv.org/abs/2511.20800 · HTML: https://mlsanity.com/paper/2511.20800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 30 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Understanding the Difficulty of Training Transformers](https://mlsanity.com/paper/2004.08249/) (2020)
- [Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks](https://mlsanity.com/paper/1806.05393/) (2018)
- [Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks](https://mlsanity.com/paper/1810.12348/) (2018)
- [An Empirical Study of Spatial Attention Mechanisms in Deep Networks](https://mlsanity.com/paper/1904.05873/) (2019)
- [Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications](https://mlsanity.com/paper/2401.06197/) (2024)
- [Global Context Networks](https://mlsanity.com/paper/2012.13375/) (2020)
- [Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation](https://mlsanity.com/paper/1910.02940/) (2019)
- [Active Convolution: Learning the Shape of Convolution for Image Classification](https://mlsanity.com/paper/1703.09076/) (2017)

## Abstract (arXiv)

Dynamic sampling mechanisms in deep learning architectures have demonstrated utility across many computer vision models, though the theoretical analysis of these structures has not yet been unified. In this paper we connect the various dynamic sampling methods by developing and analyzing a novel operator which generalizes existing methods, which we term "warping". Warping provides a minimal implementation of dynamic sampling which is amenable to analysis, and can be used to reconstruct existing architectures including deformable convolutions, active convolutional units, and spatial transformer networks. Using our formalism, we provide statistical analysis of the operator by modeling the inputs as both IID variables and homogeneous random fields. Extending this analysis, we discover a unique asymmetry between the forward and backward pass of the model training. We demonstrate that these mechanisms represent an entirely different class of orthogonal operators to the traditional translationally invariant operators defined by convolutions. With a combination of theoretical analysis and empirical investigation, we find the conditions necessary to ensure stable training of dynamic sampling networks. In addition, statistical analysis of discretization effects are studied. Finally, we introduce a novel loss landscape visualization which utilizes gradient update information directly, to better understand learning behavior.