0578508 20240402214804.920231124235959.9 14 s. E cav_un_epca*05785071-14AberdeenBMVA2023 H-NeXT robustness to unseen deformations parameter-efficient roto-translation invariant network classification on unaugmented training set cav_un_auth*0438860 Karella Tomáš UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101209 Šroubek Filip UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0254045 Blažek Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101087 Flusser Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0457087 Košík Václav UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI CZ Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2023/ZOI/karella-0578508.pdf GA21-03921S GA ČR cav_un_auth*0412209 The widespread popularity of equivariant networks underscores the significance of parameter efficient models and effective use of training data. At a time when robustness to unseen deformations is becoming increasingly important, we present H-NeXt, which bridges the gap between equivariance and invariance. H-NeXt is a parameter-efficient roto-translation invariant network that is trained without a single augmented image in the training set. Our network comprises three components: an equivariant backbone for learning roto-translation independent features, an invariant pooling layer for discarding roto-translation information, and a classification layer. H-NeXt outperforms the state of the art in classification on unaugmented training sets and augmented test sets of MNIST and CIFAR-10 cav_un_auth*0458470 British Machine Vision Conference 2023 /34./ 20231120 20231124 Aberdeen GB JD 20000 20200 20206 2024 5 PR RVO:67985556 https://hdl.handle.net/11104/0347650 S 2023 SCOPUS PUBMED WOS cav_un_epca*0578507 34th British Machine Vision Conference 2023 BMVA 2023 Aberdeen 1 14