{"url":"/method/fbnet-block","slug":"fbnet-block","name":"FBNet Block","full_name":"FBNet Block","full_name_withheld":false,"description_markdown":"**FBNet Block** is an image model block used in the [FBNet](https://paperswithcode.com/method/fbnet) architectures discovered through [DNAS](https://paperswithcode.com/method/dnas) [neural architecture search](https://paperswithcode.com/method/neural-architecture-search). The basic building blocks employed are [depthwise convolutions](https://paperswithcode.com/method/depthwise-convolution) and a [residual connection](https://paperswithcode.com/method/residual-connection).","description_state":"present","introduced_year":null,"introduced_by":{"title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","paper":"/paper/fbnet-hardware-aware-efficient-convnet-design","first_author":"Bichen Wu","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fbnet-hardware-aware-efficient-convnet-design"},"source":{"url":"https://arxiv.org/abs/1812.03443v3","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/AnnaAraslanova/FBNet/blob/ad683c69fa3029cfea5d819613bf8d4691fd2b91/fbnet_building_blocks/fbnet_builder.py#L451","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Skip Connection Blocks","url":"/methods/category/skip-connection-blocks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":null,"title":"Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search","date":"2023-06-04","arxiv_id":"2306.02459","n_code_links":0,"syntology":null},{"paper":"/paper/fbnet-feedback-network-for-point-cloud","title":"FBNet: Feedback Network for Point Cloud Completion","date":"2022-10-08","arxiv_id":"2210.03974","n_code_links":1,"syntology":null},{"paper":null,"title":"Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-scripts-with-a-memory-of-natural","title":"Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback","date":"2021-12-16","arxiv_id":"2112.09737","n_code_links":1,"syntology":null},{"paper":null,"title":"FBNet: Feature Balance Network for Urban-Scene Segmentation","date":"2021-11-05","arxiv_id":"2111.03286","n_code_links":0,"syntology":null},{"paper":null,"title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","date":"2021-04-26","arxiv_id":"2104.12766","n_code_links":0,"syntology":null},{"paper":"/paper/hw-nas-bench-hardware-aware-neural-1","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","date":"2021-03-19","arxiv_id":"2103.10584","n_code_links":1,"syntology":null},{"paper":null,"title":"HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation","date":"2020-10-06","arxiv_id":"2010.02680","n_code_links":0,"syntology":null},{"paper":"/paper/hit-detector-hierarchical-trinity","title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","date":"2020-03-26","arxiv_id":"2003.11818","n_code_links":1,"syntology":null},{"paper":"/paper/hardware-aware-neural-network-architectures","title":"Hardware Aware Neural Network Architectures using FbNet","date":"2019-06-17","arxiv_id":"1906.07214","n_code_links":1,"syntology":null},{"paper":"/paper/fbnet-hardware-aware-efficient-convnet-design","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","date":"2018-12-09","arxiv_id":"1812.03443","n_code_links":5,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}}],"papers_shown":12,"tasks":[{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":7},{"task":"/task/hardware-aware-neural-architecture-search","name":"Hardware Aware Neural Architecture Search","papers":4},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/script-generation","name":"Script Generation","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/point-cloud-completion","name":"Point Cloud Completion","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/scene-segmentation","name":"Scene Segmentation","papers":1}],"tasks_shown":20,"n_tasks":22,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":1},{"year":"2020","papers":2},{"year":"2021","papers":5},{"year":"2022","papers":2},{"year":"2023","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/fbnet-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}