{"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/learning-deep-compositional-grammatical","title":"AOGNets: Compositional Grammatical Architectures for Deep Learning","arxiv_id":"1711.05847","date":"2017-11-15","proceeding":"CVPR 2019 6","authors":["Xilai Li","Xi Song","Tianfu Wu"],"abstract":"Neural architectures are the foundation for improving performance of deep\nneural networks (DNNs). This paper presents deep compositional grammatical\narchitectures which harness the best of two worlds: grammar models and DNNs.\nThe proposed architectures integrate compositionality and reconfigurability of\nthe former and the capability of learning rich features of the latter in a\nprincipled way. We utilize AND-OR Grammar (AOG) as network generator in this\npaper and call the resulting networks AOGNets. An AOGNet consists of a number\nof stages each of which is composed of a number of AOG building blocks. An AOG\nbuilding block splits its input feature map into N groups along feature\nchannels and then treat it as a sentence of N words. It then jointly realizes a\nphrase structure grammar and a dependency grammar in bottom-up parsing the\n\"sentence\" for better feature exploration and reuse. It provides a unified\nframework for the best practices developed in state-of-the-art DNNs. In\nexperiments, AOGNet is tested in the CIFAR-10, CIFAR-100 and ImageNet-1K\nclassification benchmark and the MS-COCO object detection and segmentation\nbenchmark. In CIFAR-10, CIFAR-100 and ImageNet-1K, AOGNet obtains better\nperformance than ResNet and most of its variants, ResNeXt and its attention\nbased variants such as SENet, DenseNet and DualPathNet. AOGNet also obtains the\nbest model interpretability score using network dissection. AOGNet further\nshows better potential in adversarial defense. In MS-COCO, AOGNet obtains\nbetter performance than the ResNet and ResNeXt backbones in Mask R-CNN.","url_abs":"http://arxiv.org/abs/1711.05847v3","url_pdf":"http://arxiv.org/pdf/1711.05847v3.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":"learning-deep-compositional-grammatical","repo_url":"https://github.com/iVMCL/AOGNets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-deep-compositional-grammatical","repo_url":"https://github.com/iVMCL/AOGNet-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-deep-compositional-grammatical","repo_url":"https://github.com/ivMCL/AttentiveNorm_Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-deep-compositional-grammatical","repo_url":"https://github.com/xilaili/AOGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"object-detection-1","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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"interpretability","method_name":"Interpretability"},{"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":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"senet","method_name":"SENet"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.05847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05847"}},"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/ivMCL/AttentiveNorm_Detection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iVMCL/AOGNet-v2","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iVMCL/AOGNets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xilaili/AOGNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":7,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"501b6fc8579e0ee3","entry":"aog_block","repo":"xilaili/AOGNet","repo_kind":"listed","path":"symbol/symbol_aognet.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/symbol/symbol_aognet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"501b6fc8579e0ee3"}},{"code_sha256_prefix":"bd0445711ecccc1e","entry":"aog_unit","repo":"xilaili/AOGNet","repo_kind":"listed","path":"symbol/symbol_aognet.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/symbol/symbol_aognet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd0445711ecccc1e"}},{"code_sha256_prefix":"cb9ecf3a1a2ecb5a","entry":"get_aog","repo":"iVMCL/AOGNets","repo_kind":"official","path":"backbones/aognet/AOG.py","file_url":"https://github.com/iVMCL/AOGNets/blob/HEAD/backbones/aognet/AOG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cb9ecf3a1a2ecb5a"}},{"code_sha256_prefix":"1f051511be4bd045","entry":"get_aog","repo":"xilaili/AOGNet","repo_kind":"listed","path":"aognet/aog/aog_1d.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/aognet/aog/aog_1d.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f051511be4bd045"}},{"code_sha256_prefix":"4797e867dbe4c93c","entry":"get_symbol","repo":"xilaili/AOGNet","repo_kind":"listed","path":"symbol/symbol_aognet.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/symbol/symbol_aognet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4797e867dbe4c93c"}},{"code_sha256_prefix":"5561884c30661353","entry":"is_param","repo":"xilaili/AOGNet","repo_kind":"listed","path":"aognet/utils/memonger.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/aognet/utils/memonger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5561884c30661353"}},{"code_sha256_prefix":"9111a4430576d5c3","entry":"make_mirror_plan","repo":"xilaili/AOGNet","repo_kind":"listed","path":"aognet/utils/memonger.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/aognet/utils/memonger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9111a4430576d5c3"}},{"code_sha256_prefix":"d4bf79898fff9b84","entry":"prod","repo":"xilaili/AOGNet","repo_kind":"listed","path":"aognet/utils/memonger.py","file_url":"https://github.com/xilaili/AOGNet/blob/HEAD/aognet/utils/memonger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4bf79898fff9b84"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}