{"url":"/method/dice-unit","slug":"dice-unit","name":"DiCE Unit","full_name":"DiCE Unit","full_name_withheld":false,"description_markdown":"A **DiCE Unit** is an image model block that is built using dimension-wise convolutions and dimension-wise fusion.  The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE unit to efficiently encode spatial and channel-wise information contained in the input tensor. \r\n\r\nStandard convolutions encode spatial and channel-wise information simultaneously, but they are computationally expensive. To improve the efficiency of standard convolutions, separable [convolution](https://paperswithcode.com/method/convolution) are introduced, where spatial and channelwise information are encoded separately using depth-wise and point-wise convolutions, respectively. Though this factorization is effective, it puts a significant computational load on point-wise convolutions and makes them a computational bottleneck.\r\n\r\nDiCE Units utilize a dimension-wise convolution to encode depth-wise, width-wise, and height-wise information independently. The dimension-wise convolutions encode local information from different dimensions of the input tensor, but do not capture global information. One approach is a [pointwise convolution](https://paperswithcode.com/method/pointwise-convolution), but it is computationally expensive, so instead dimension-wise fusion factorizes the point-wise convolution in two steps: (1) local fusion and (2) global fusion.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","paper":"/paper/dicenet-dimension-wise-convolutions-for","first_author":"Sachin Mehta","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/dicenet-dimension-wise-convolutions-for"},"source":{"url":"https://arxiv.org/abs/1906.03516v3","title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/sacmehta/EdgeNets/blob/c4c515700df32bb0417de3dd1eb39cfe23bf9148/model/classification/dicenet.py#L14","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":1,"papers_newest_first":[{"paper":"/paper/dicenet-dimension-wise-convolutions-for","title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","date":"2019-06-08","arxiv_id":"1906.03516","n_code_links":2,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}}],"papers_shown":1,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":1},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","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":8,"n_tasks":8,"usage_by_year":[{"year":"2019","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/dice-unit"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}