{"url":"/method/harmonic-block","slug":"harmonic-block","name":"Harmonic Block","full_name":"Harmonic Block","full_name_withheld":false,"description_markdown":"A **Harmonic Block** is an image model component that utilizes [Discrete Cosine Transform](https://paperswithcode.com/method/discrete-cosine-transform) (DCT) filters. Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, DCT has preset spectral filters, which can be better for compressing information (due to the presence of redundancy in the spectral domain).\r\n\r\nDCT has been successfully used for JPEG encoding to transform image blocks into spectral representations to capture the most information with a small number of coefficients. Harmonic blocks learn how to optimally combine spectral coefficients at every layer to produce a fixed size representation defined as a weighted sum of responses to DCT filters. The use of DCT filters allows to address the task of model compression.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2001.06570v3","title":"Harmonic Convolutional Networks based on Discrete Cosine Transform","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/matej-ulicny/harmonic-networks/blob/0fccf674806a0b876e641ef5271aad520ff90739/imagenet/models/resnet.py#L71","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/harmonic-convolutional-networks-based-on","title":"Harmonic Convolutional Networks based on Discrete Cosine Transform","date":"2020-01-18","arxiv_id":"2001.06570","n_code_links":1,"syntology":{"ran":0,"of":10,"unverified":10,"pointer_only":0}}],"papers_shown":1,"tasks":[{"task":"/task/edge-detection","name":"Edge Detection","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/harmonic-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}