mlsanityData to 7 Oct 2026

Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognition

arXiv 2112.14804 ↗First posted 29 Dec 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adaptive squeeze-excitation (SASE) modules for image synthesis and image recognition respectively. For image synthesis tasks, the proposed SASE is tested in both low-shot and one-shot learning tasks. It shows better performance than prior arts. For image recognition tasks, the proposed SASE is used as a drop-in replacement for convolution layers in ResNets and achieves much better accuracy than the vanilla ResNets, and slightly better than the MHSA counterparts such as the Swin-Transformer and Pyramid-Transformer in the ImageNet-1000 dataset, with significantly smaller models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 29 Dec 2021.

Builds on

42 of 54 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2017Mask R-CNNcited by 7,259
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
30 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2015Spatial Transformer Networkscited by 1,423
  3. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  5. 2018Demystifying MMD GANscited by 1,268
  6. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2016Language Modeling with Gated Convolutional Networkscited by 688
  9. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  10. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  11. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  12. 2019Attention Augmented Convolutional Networkscited by 363
  13. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  14. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  15. 2014Recurrent Models of Visual Attentioncited by 344
  16. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  17. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  18. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  19. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  20. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 138
  21. 2019Image Synthesis From Reconfigurable Layout and Stylecited by 85
  22. 2020Image Augmentations for GAN Trainingcited by 78
  23. 2020Improved Techniques for Training Single-Image GANscited by 77
  24. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  25. 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
  26. 2019Detecting Overfitting of Deep Generative Networks via Latent Recoverycited by 44
  27. 2018A Large-Scale Study on Regularization and Normalization in GANscited by 26
  28. 2020On Data Augmentation for GAN Trainingcited by 25
  29. 2013Provable Bounds for Learning Some Deep Representationscited by 14
  30. 2019Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translationcited by 1

Built on by

Not cited yet.