{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/lip-local-importance-based-pooling","title":"LIP: Local Importance-based Pooling","arxiv_id":"1908.04156","date":"2019-08-12","proceeding":"ICCV 2019 10","authors":["Ziteng Gao","Li-Min Wang","Gangshan Wu"],"abstract":"Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strategies, which could hinder the learning process and eventually result in suboptimal models. In this paper, we present a unified framework over the existing downsampling layers (e.g., average pooling, max pooling, and strided convolution) from a local importance view. In this framework, we analyze the issues of these widely-used pooling layers and figure out the criteria for designing an effective downsampling layer. According to this analysis, we propose a conceptually simple, general, and effective pooling layer based on local importance modeling, termed as {\\em Local Importance-based Pooling} (LIP). LIP can automatically enhance discriminative features during the downsampling procedure by learning adaptive importance weights based on inputs. Experiment results show that LIP consistently yields notable gains with different depths and different architectures on ImageNet classification. In the challenging MS COCO dataset, detectors with our LIP-ResNets as backbones obtain a consistent improvement ($\\ge 1.4\\%$) over the vanilla ResNets, and especially achieve the current state-of-the-art performance in detecting small objects under the single-scale testing scheme.","url_abs":"https://arxiv.org/abs/1908.04156v3","url_pdf":"https://arxiv.org/pdf/1908.04156v3.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":"lip-local-importance-based-pooling","repo_url":"https://github.com/sebgao/LIP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","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":"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":"fcn","method_name":"FCN"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"local-importance-based-pooling","method_name":"Local Importance-based Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"local-importance-based-pooling","name":"Local Importance-based Pooling","full_name":"Local Importance-based Pooling"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"LIP-ResNet-101","rank_in_archive_order":764,"of":1060,"metrics":{"Number of params":"42.9M","Top 1 Accuracy":"79.33%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-50 (LIP Bottleneck-256)","rank_in_archive_order":850,"of":1060,"metrics":{"Number of params":"25.8M","Top 1 Accuracy":"78.15%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"LIP-DenseNet-BC-121","rank_in_archive_order":907,"of":1060,"metrics":{"Number of params":"8.7M","Top 1 Accuracy":"76.64%"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Faster R-CNN (LIP-ResNet-101)","rank_in_archive_order":161,"of":220,"metrics":{"AP50":"63.6","AP75":"45.6","APM":"45.8","APS":"25.2","box AP":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Faster R-CNN (LIP-ResNet-101-MD w FPN)","rank_in_archive_order":151,"of":225,"metrics":{"AP50":"65.7","AP75":"48.1","APL":"56.3","APM":"46.7","APS":"25.4","box mAP":"43.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.04156","atlas_url":"https://app.syntology.ai/?focus=1908.04156","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1908.04156"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1908.04156\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1908.04156"},"call":"get_concepts_for_paper(arxiv_id=\"1908.04156\")"}],"by_repo":[{"repo":"sebgao/LIP","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dbe025c654e9f0d7eaa5454cf449e50e835c0f85bae15455f318ab1f1a0fd90a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}