{"url":"/method/sniper","slug":"sniper","name":"SNIPER","full_name":"SNIPER","full_name_withheld":false,"description_markdown":"**SNIPER** is a multi-scale training approach for instance-level recognition tasks like object detection and instance-level segmentation. Instead of processing all pixels in an image pyramid, SNIPER selectively processes context regions around the ground-truth objects (a.k.a chips). This can help to speed up multi-scale training as it operates on low-resolution chips. Due to its memory-efficient design, SNIPER can benefit from [Batch Normalization](https://paperswithcode.com/method/batch-normalization) during training and it makes larger batch-sizes possible for instance-level recognition tasks on a single GPU.","description_state":"present","introduced_year":null,"introduced_by":{"title":"SNIPER: Efficient Multi-Scale Training","paper":"/paper/sniper-efficient-multi-scale-training","first_author":"Bharat Singh","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sniper-efficient-multi-scale-training"},"source":{"url":"http://arxiv.org/abs/1805.09300v3","title":"SNIPER: Efficient Multi-Scale Training","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":"Multi-Scale Training","url":"/methods/category/multi-scale-training","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":"/paper/cfaults-model-based-diagnosis-for-fault","title":"CFaults: Model-Based Diagnosis for Fault Localization in C Programs with Multiple Test Cases","date":"2024-07-12","arxiv_id":"2407.09337","n_code_links":1,"syntology":null},{"paper":null,"title":"SNIPER Training: Single-Shot Sparse Training for Text-to-Speech","date":"2022-11-14","arxiv_id":"2211.07283","n_code_links":0,"syntology":null},{"paper":"/paper/scale-normalized-image-pyramids-with","title":"Scale Normalized Image Pyramids with AutoFocus for Object Detection","date":"2021-02-10","arxiv_id":"2102.05646","n_code_links":1,"syntology":null},{"paper":null,"title":"Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance","date":"2018-10-15","arxiv_id":"1810.06208","n_code_links":0,"syntology":null},{"paper":"/paper/sniper-efficient-multi-scale-training","title":"SNIPER: Efficient Multi-Scale Training","date":"2018-05-23","arxiv_id":"1805.09300","n_code_links":4,"syntology":null}],"papers_shown":5,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/fault-localization","name":"Fault localization","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/region-proposal","name":"Region Proposal","papers":1},{"task":"/task/tag","name":"TAG","papers":1},{"task":"/task/text-to-speech","name":"Text to Speech","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2018","papers":2},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2024","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/sniper"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}