{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chex-channel-exploration-for-cnn-model","title":"CHEX: CHannel EXploration for CNN Model Compression","arxiv_id":"2203.15794","date":"2022-03-29","proceeding":"CVPR 2022 1","authors":["Zejiang Hou","Minghai Qin","Fei Sun","Xiaolong Ma","Kun Yuan","Yi Xu","Yen-Kuang Chen","Rong Jin","Yuan Xie","Sun-Yuan Kung"],"abstract":"Channel pruning has been broadly recognized as an effective technique to reduce the computation and memory cost of deep convolutional neural networks. However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model. Such limitations may lead to sub-optimal model quality as well as excessive memory and training cost. In this paper, we propose a novel Channel Exploration methodology, dubbed as CHEX, to rectify these problems. As opposed to pruning-only strategy, we propose to repeatedly prune and regrow the channels throughout the training process, which reduces the risk of pruning important channels prematurely. More exactly: From intra-layer's aspect, we tackle the channel pruning problem via a well known column subset selection (CSS) formulation. From inter-layer's aspect, our regrowing stages open a path for dynamically re-allocating the number of channels across all the layers under a global channel sparsity constraint. In addition, all the exploration process is done in a single training from scratch without the need of a pre-trained large model. Experimental results demonstrate that CHEX can effectively reduce the FLOPs of diverse CNN architectures on a variety of computer vision tasks, including image classification, object detection, instance segmentation, and 3D vision. For example, our compressed ResNet-50 model on ImageNet dataset achieves 76% top1 accuracy with only 25% FLOPs of the original ResNet-50 model, outperforming previous state-of-the-art channel pruning methods. The checkpoints and code are available at here .","url_abs":"https://arxiv.org/abs/2203.15794v1","url_pdf":"https://arxiv.org/pdf/2203.15794v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"chex-channel-exploration-for-cnn-model","repo_url":"https://github.com/zejiangh/Filter-GaP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"model","task_name":"model"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.15794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15794"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zejiangh/Filter-GaP","reach":null}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"1042b26c4fe40c4d","entry":"CSS","repo":"zejiangh/Filter-GaP","repo_kind":"listed","path":"CLS/image_classification/prune_utils.py","file_url":"https://github.com/zejiangh/Filter-GaP/blob/HEAD/CLS/image_classification/prune_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1042b26c4fe40c4d"}},{"code_sha256_prefix":"ecfd1ac200576251","entry":"L1_norm","repo":"zejiangh/Filter-GaP","repo_kind":"listed","path":"CLS/image_classification/prune_utils.py","file_url":"https://github.com/zejiangh/Filter-GaP/blob/HEAD/CLS/image_classification/prune_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ecfd1ac200576251"}},{"code_sha256_prefix":"392b44de894819ab","entry":"update_channel_mask","repo":"zejiangh/Filter-GaP","repo_kind":"listed","path":"CLS/image_classification/prune_utils.py","file_url":"https://github.com/zejiangh/Filter-GaP/blob/HEAD/CLS/image_classification/prune_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"392b44de894819ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}