mlsanityData to 7 Oct 2026

LiftPool: Bidirectional ConvNet Pooling

arXiv 2104.00996 ↗First posted 2 Apr 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a lossy process. Moreover, they are not invertible: upsampling a downscaled feature map can not recover the lost information in the downsampling. By adopting the philosophy of the classical Lifting Scheme from signal processing, we propose LiftPool for bidirectional pooling layers, including LiftDownPool and LiftUpPool. LiftDownPool decomposes a feature map into various downsized sub-bands, each of which contains information with different frequencies. As the pooling function in LiftDownPool is perfectly invertible, by performing LiftDownPool backward, a corresponding up-pooling layer LiftUpPool is able to generate a refined upsampled feature map using the detail sub-bands, which is useful for image-to-image translation challenges. Experiments show the proposed methods achieve better results on image classification and semantic segmentation, using various backbones. Moreover, LiftDownPool offers better robustness to input corruptions and perturbations.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 2 Apr 2021.

Builds on

22 of 42 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  11. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  12. 2018i-RevNet: Deep Invertible Networkscited by 137
10 more
  1. 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
  2. 2015Spectral Representations for Convolutional Neural Networkscited by 79
  3. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  4. 2013Stochastic Pooling for Regularization of Deep Convolutional Neural Networkscited by 48
  5. 2015Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Treecited by 36
  6. 2019Pixelated Semantic Colorizationcited by 28
  7. 2018Detail-Preserving Pooling in Deep Networkscited by 26
  8. 2016S3Pool: Pooling with Stochastic Spatial Samplingcited by 17
  9. 2019Deep Adaptive Wavelet Networkcited by 16
  10. 2019Semi-Conditional Normalizing Flows for Semi-Supervised Learningcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 2; 2025: 1; 2026: 2.

11 papers.

  1. 2021AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsamplingcited by 47
  2. 2022Temporal Lift Pooling for Continuous Sign Language Recognitioncited by 26
  3. 2021Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networkscited by 3
  4. 2024NOAH: Learning Pairwise Object Category Attentions for Image Classificationcited by 2
  5. 2022Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpoolingcited by 1
  6. 2023Progressive Meta-Pooling Learning for Lightweight Image Classification Modelcited by 1
  7. 2025Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognitioncited by 1
  8. 2023A Novel Dual-pooling Attention Module for UAV Vehicle Re-identificationcited by 0
  9. 2024Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibrationcited by 0
  10. 2026Redefining the Down-Sampling Scheme of U-Net for Precision Biomedical Image Segmentationcited by 0
  11. 2026Task-Relevant Null-Space Residuals for Non-Injective Neural Mappingscited by 0