{"url":"/method/groupdnet","slug":"groupdnet","name":"GroupDNet","full_name":"Group Decreasing Network","full_name_withheld":false,"description_markdown":"**Group Decreasing Network**, or **GroupDNet**, is a type of convolutional neural network for multi-modal image synthesis. GroupDNet contains one encoder and one decoder. Inspired by the idea of [VAE](https://paperswithcode.com/method/vae) and SPADE, the encoder $E$ produces a\r\nlatent code $Z$ that is supposed to follow a Gaussian distribution $\\mathcal{N}(0,1)$ during training. While testing, the encoder $E$ is discarded. A randomly sampled code from the Gaussian distribution substitutes for $Z$. To fulfill this, the re-parameterization trick is used to enable a differentiable loss function during training. Specifically, the encoder predicts a mean vector and a variance vector through two fully connected layers to represent the encoded distribution. The gap between the encoded distribution and Gaussian distribution can be minimized by imposing a KL-divergence loss.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Semantically Multi-modal Image Synthesis","paper":"/paper/semantically-mutil-modal-image-synthesis","first_author":"Zhen Zhu","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/semantically-mutil-modal-image-synthesis"},"source":{"url":"https://arxiv.org/abs/2003.12697v3","title":"Semantically Multi-modal Image Synthesis","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Generation Models","url":"/methods/category/image-generation-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/semantically-mutil-modal-image-synthesis","title":"Semantically Multi-modal Image Synthesis","date":"2020-03-28","arxiv_id":"2003.12697","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/groupdnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}