{"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/spatial-group-wise-enhance-improving-semantic","title":"Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks","arxiv_id":"1905.09646","date":"2019-05-23","proceeding":null,"authors":["Xiang Li","Xiaolin Hu","Jian Yang"],"abstract":"The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the feature vector of each layer, representing various semantic entities. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with \\emph{almost no extra parameters and calculations}. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2\\% Top-1 accuracy improvement on the ImageNet benchmark and 1.0$\\sim$2.0\\% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at https://github.com/implus/PytorchInsight.","url_abs":"https://arxiv.org/abs/1905.09646v2","url_pdf":"https://arxiv.org/pdf/1905.09646v2.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":"spatial-group-wise-enhance-improving-semantic","repo_url":"https://github.com/implus/PytorchInsight","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"spatial-group-wise-enhance-improving-semantic","repo_url":"https://github.com/whai362/PytorchInsight","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"spatial-group-wise-enhance-improving-semantic","repo_url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/SGE.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"cascade-r-cnn","method_name":"Cascade R-CNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"retinanet","method_name":"RetinaNet"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-group-wise-enhance","method_name":"Spatial Group-wise Enhance"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SGE-ResNet101","rank_in_archive_order":806,"of":1060,"metrics":{"GFLOPs":"7.858","Number of params":"44.55M","Top 1 Accuracy":"78.798%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SGE-ResNet50","rank_in_archive_order":870,"of":1060,"metrics":{"GFLOPs":"4.127","Number of params":"25.56M","Top 1 Accuracy":"77.584%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.09646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09646"}},"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/implus/PytorchInsight","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whai362/PytorchInsight","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/SGE.py","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"77f89e05c55c985d","entry":"conv3x3","repo":"whai362/PytorchInsight","repo_kind":"listed","path":"detection/mmdet/models/backbones/resnet_sge.py","file_url":"https://github.com/whai362/PytorchInsight/blob/HEAD/detection/mmdet/models/backbones/resnet_sge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77f89e05c55c985d"}},{"code_sha256_prefix":"af749ed3474a8d84","entry":"make_res_layer","repo":"whai362/PytorchInsight","repo_kind":"listed","path":"detection/mmdet/models/backbones/resnet_sge.py","file_url":"https://github.com/whai362/PytorchInsight/blob/HEAD/detection/mmdet/models/backbones/resnet_sge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af749ed3474a8d84"}},{"code_sha256_prefix":"de955f3e3ead10d1","entry":"conv1x1","repo":"whai362/PytorchInsight","repo_kind":"listed","path":"classification/models/imagenet/resnet_sge.py","file_url":"https://github.com/whai362/PytorchInsight/blob/HEAD/classification/models/imagenet/resnet_sge.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de955f3e3ead10d1"}},{"code_sha256_prefix":"cddb8eda1eb5217a","entry":"conv3x3","repo":"whai362/PytorchInsight","repo_kind":"listed","path":"classification/models/imagenet/resnet_sge.py","file_url":"https://github.com/whai362/PytorchInsight/blob/HEAD/classification/models/imagenet/resnet_sge.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cddb8eda1eb5217a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}