REVIEW 5 cited by
How Much Position Information Do Convolutional Neural Networks Encode?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is looking at, but not where it is positioned in the image. Information concerning absolute position is inherently useful, and it is reasonable to assume that deep CNNs may implicitly learn to encode this information if there is a means to do so. In this paper, we test this hypothesis revealing the surprising degree of absolute position information that is encoded in commonly used neural networks. A comprehensive set of experiments show the validity of this hypothesis and shed light on how and where this information is represented while offering clues to where positional information is derived from in deep CNNs.
Forward citations
Cited by 5 Pith papers
-
A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues
A physics-flavored CNN-transformer automatically fits stretched-exponential parameters to engineered skeletal muscle contraction curves, using synthetic pre-training and unsupervised real-data alignment.
-
A physics-informed neural network for improving surface reconstruction of intracranial saccular aneurysms via variational membrane equilibrium
The paper introduces a PINN/B-spline reconstruction pipeline that filters imaging artifacts from aneurysm surfaces by enforcing a Laplace membrane-equilibrium loss, and claims cleaner rupture-risk maps concentrated at...
-
Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling
Survey organizing panoramic scene analysis literature by architectural design and training paradigm, identifying the absence of methods achieving both strict spherical equivariance and full reuse of perspective-pretra...
-
The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathology
EAGLE-Net adds spatial encoding and a top-K neighborhood loss to attention-based MIL, achieving modest accuracy gains and more coherent attention maps on pan-cancer histology benchmarks.
-
ARMA Block: A CNN-Based Autoregressive and Moving Average Module for Long-Term Time Series Forecasting
A two-branch convolutional ARMA block with residual refinement matches or beats older linear and transformer baselines on several long-term forecasting benchmarks with trend shifts, and appears to encode position information.
Discussion (0). Continue with ORCID to comment.