mlsanityData to 7 Oct 2026

Analysis of Branch Specialization and its Application in Image Decomposition

arXiv 2206.05810 ↗First posted 12 Jun 2022cs.CV cs.LG cs.NEcited by 2

Not on the map. Why?

Abstract (arXiv)

Branched neural networks have been used extensively for a variety of tasks. Branches are sub-parts of the model that perform independent processing followed by aggregation. It is known that this setting induces a phenomenon called Branch Specialization, where different branches become experts in different sub-tasks. Such observations were qualitative by nature. In this work, we present a methodological analysis of Branch Specialization. We explain the role of gradient descent in this phenomenon. We show that branched generative networks naturally decompose animal images to meaningful channels of fur, whiskers and spots and face images to channels such as different illumination components and face parts.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

20 of 36 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  9. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  10. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  11. 2017Empirical Analysis of the Hessian of Over-Parametrized Neural Networkscited by 283
  12. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
8 more
  1. 2018A Convergence Analysis of Gradient Descent for Deep Linear Neural Networkscited by 180
  2. 2016Eigenvalues of the Hessian in Deep Learning: Singularity and Beyondcited by 156
  3. 2017Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learningcited by 125
  4. 2013Deep Learning of Representations: Looking Forwardcited by 84
  5. 2018Modular Networks: Learning to Decompose Neural Computationcited by 62
  6. 2013Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networkscited by 44
  7. 2019Hessian based analysis of SGD for Deep Nets: Dynamics and Generalizationcited by 37
  8. 2022Beyond Fixation: Dynamic Window Visual Transformercited by 28

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Additive Class Distinction Maps using Branched-GANscited by 0
  2. 2023DXAI: Explaining Classification by Image Decompositioncited by 0