FlexPooling with Simple Auxiliary Classifiers in Deep Networks

• URL: http://arxiv.org/abs/2606.14926v1
• Date: Fri, 12 Jun 2026 20:04:00 GMT
• Title: FlexPooling with Simple Auxiliary Classifiers in Deep Networks
• Abstract summary: Pooling is an essential operation in convolutional neural networks (CNNs)<n>We propose FlexPooling, which generalizes average pooling by learning a weighted average over activations jointly with the rest of the network.<n>Experiments show that FlexPooling consistently outperforms baseline networks, achieving approximately 1 to 3 percent improvement in accuracy.
• Score: 12.728008452578427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In computer vision, the basic pipeline of most convolutional neural networks consists of multiple feature extraction layers, where the input signal is downsampled to a lower resolution in each subsequent layer. This downsampling process is commonly referred to as pooling, which is an essential operation in CNNs. Pooling improves robustness against transformations, reduces the number of trainable parameters, increases the receptive field, and lowers computation time. Since pooling is a lossy process but remains important for extracting high-level information from low-level representations, it is important to preserve the most prominent information from previous activations to improve network discriminability. Standard pooling is usually performed using dense pooling methods, such as max pooling or average pooling, or through strided convolutional kernels. In this paper, we propose a simple yet effective adaptive pooling method, called FlexPooling, which generalizes average pooling by learning a weighted average over activations jointly with the rest of the network. We further show that attaching Simple Auxiliary Classifiers (SAC) to the CNN improves performance and demonstrates the effectiveness of the proposed method compared with standard pooling methods. Experiments on multiple popular image classification datasets show that FlexPooling consistently outperforms baseline networks, achieving approximately 1 to 3 percent improvement in accuracy.

Related papers

• Stochastic Subsampling With Average Pooling [7.229820415732795]
  We propose a new module called average pooling, which incorporates Dropout-likeity in pooling. We describe the properties of subsampling and average pooling and leverage them to design a module without any inconsistency problem. The average pooling achieves a regularization effect without any potential performance degradation due to the inconsistency issue and can easily be plugged into existing deep neural networks.
  arXiv  Detail & Related papers  (2024-09-25T05:18:17Z)
• Simple Pooling Front-ends For Efficient Audio Classification [56.59107110017436]
  We show that eliminating the temporal redundancy in the input audio features could be an effective approach for efficient audio classification. We propose a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information. SimPFs can achieve a reduction in more than half of the number of floating point operations for off-the-shelf audio neural networks.
  arXiv  Detail & Related papers  (2022-10-03T14:00:41Z)
• Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling [101.72318949104627]
  We propose a novel framework of hierarchical convolutional neural networks (HS-CNNs) with a lifting structure to learn adaptive spherical wavelets for pooling and unpooling. LiftHS-CNN ensures a more efficient hierarchical feature learning for both image- and pixel-level tasks.
  arXiv  Detail & Related papers  (2022-05-31T07:23:42Z)
• AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling [82.08631594071656]
  Pooling layers are essential building blocks of Convolutional Neural Networks (CNNs) We propose an adaptive and exponentially weighted pooling method named adaPool. We demonstrate how adaPool improves the preservation of detail through a range of tasks including image and video classification and object detection.
  arXiv  Detail & Related papers  (2021-11-01T08:50:37Z)
• Ordinal Pooling [26.873004843826962]
  Ordinal pooling rearranges elements of a pooling region in a sequence and assigns a different weight to each element based upon its order in the sequence. Experiments suggest that it is advantageous for the networks to perform different types of pooling operations within a pooling layer.
  arXiv  Detail & Related papers  (2021-09-03T14:33:02Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Refining activation downsampling with SoftPool [74.1840492087968]
  Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. We propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. We show that SoftPool can retain more information in the reduced activation maps.
  arXiv  Detail & Related papers  (2021-01-02T12:09:49Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection [21.48875255723581]
  A mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results.
  arXiv  Detail & Related papers  (2019-12-29T14:11:33Z)

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.