We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field size, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field size. We analyze the effective receptive field in several architecture designs, and the effect of sub-sampling, skip connections, dropout and nonlinear activations on it. This leads to suggestions for ways to address its tendency to be too small.

We study characteristics of receptive fields of units in deep convolutional networks.

Due to its ability to integrate information over large boxes, the new layer facilitates long-range propagation of information and leads to the efficient increase of the receptive fields of network units.

"Green", "Orange", and "Blue" denote the results from models trained on

Message-Passing Neural Networks (MPNNs) have become a cornerstone for processing and analyzing graph-structured data. However, their effectiveness is often hindered by phenomena such as over-squashing, where long-range dependencies or interactions are inadequately captured and expressed in the MPNN output. This limitation mirrors the challenges of the Effective Receptive Field (ERF) in Convolutional Neural Networks (CNNs), where the theoretical receptive field is underutilized in practice. In this work, we show and theoretically explain the limited ERF problem in MPNNs. Furthermore, inspired by recent advances in ERF augmentation for CNNs, we propose an Interleaved Multiscale Message-Passing Neural Networks (IM-MPNN) architecture to address these problems in MPNNs. Our method incorporates a hierarchical coarsening of the graph, enabling message-passing across multiscale representations and facilitating long-range interactions without excessive depth or parameterization. Through extensive evaluations on benchmarks such as the Long-Range Graph Benchmark (LRGB), we demonstrate substantial improvements over baseline MPNNs in capturing long-range dependencies while maintaining computational efficiency.

In contrast to vision transformers, which model long-range dependencies through global self-attention, large kernel convolutions provide a more efficient and scalable alternative, particularly in high-resolution 3D volumetric settings. However, naively increasing kernel size often leads to optimization instability and degradation in performance. Motivated by the spatial bias observed in effective receptive fields (ERFs), we hypothesize that different kernel elements converge at variable rates during training. To support this, we derive a theoretical connection between element-wise gradients and first-order optimization, showing that structurally re-parameterized convolution blocks inherently induce spatially varying learning rates. Building on this insight, we introduce Rep3D, a 3D convolutional framework that incorporates a learnable spatial prior into large kernel training. A lightweight two-stage modulation network generates a receptive-biased scaling mask, adaptively re-weighting kernel updates and enabling local-to-global convergence behavior. Rep3D adopts a plain encoder design with large depthwise convolutions, avoiding the architectural complexity of multi-branch compositions. We evaluate Rep3D on five challenging 3D segmentation benchmarks and demonstrate consistent improvements over state-of-the-art baselines, including transformer-based and fixed-prior re-parameterization methods. By unifying spatial inductive bias with optimization-aware learning, Rep3D offers an interpretable, and scalable solution for 3D medical image analysis. The source code is publicly available at https://github.com/leeh43/Rep3D.

Another thing that is common in typical convolutional networks these days is batch normalization, which is also not discussed, but might help justify the extra assumptions needed to show that the main results hold using ReLU nonlinearities. In general I thought that the experiments could have been carried out in a more quantitative way. It's somewhat interesting that the receptive field is able to grow during training (but then again, maybe it must in order for the network to do better, and there is no reason why it can't grow at least somewhat).