% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Wang:1048850,
      author       = {Wang, Qin and Bruns, Benjamin and Scharr, Hanno and
                      Krajsek, Kai},
      title        = {{S}elf-{S}upervised {L}earning based on {T}ransformed
                      {I}mage {R}econstruction for {E}quivariance-{C}oherent
                      {F}eature {R}epresentation},
      reportid     = {FZJ-2025-04955},
      year         = {2025},
      abstract     = {The equivariant behaviour of features is essential in many
                      computer vision tasks, yet popular self-supervised learning
                      (SSL) methods tend to constrain equivariance by design. We
                      propose a self-supervised learning approach where the system
                      learns transformations independently by reconstructing
                      images that have undergone previously unseen
                      transformations. Specifically, the model is tasked to
                      reconstruct intermediate transformed images, e.g. translated
                      or rotated images, without prior knowledge of these
                      transformations. This auxiliary task encourages the model to
                      develop equivariance-coherent features without relying on
                      predefined transformation rules. To this end, we apply
                      transformations to the input image, generating an image
                      pair, and then split the extracted features into two sets
                      per image. One set is used with a usual SSL loss encouraging
                      invariance, the other with our loss based on the auxiliary
                      task to reconstruct the intermediate transformed images. Our
                      loss and the SSL loss are linearly combined with weighted
                      terms. Evaluating on synthetic tasks with natural images,
                      our proposed method strongly outperforms all competitors,
                      regardless of whether they are designed to learn
                      equivariance. Furthermore, when trained alongside
                      augmentation-based methods as the invariance tasks, such as
                      iBOT or DINOv2, we successfully learn a balanced combination
                      of invariant and equivariant features. Our approach performs
                      strong on a rich set of realistic computer vision downstream
                      tasks, almost always improving over all baselines.},
      cin          = {IAS-8 / JSC},
      cid          = {I:(DE-Juel1)IAS-8-20210421 / I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / 5112 - Cross-Domain
                      Algorithms, Tools, Methods Labs (ATMLs) and Research Groups
                      (POF4-511) / SLNS - SimLab Neuroscience (Helmholtz-SLNS)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5112 /
                      G:(DE-Juel1)Helmholtz-SLNS},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.34734/FZJ-2025-04955},
      url          = {https://juser.fz-juelich.de/record/1048850},
}