{"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/espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","arxiv_id":"1811.11431","date":"2018-11-28","proceeding":"CVPR 2019 6","authors":["Sachin Mehta","Mohammad Rastegari","Linda Shapiro","Hannaneh Hajishirzi"],"abstract":"We introduce a light-weight, power efficient, and general purpose\nconvolutional neural network, ESPNetv2, for modeling visual and sequential\ndata. Our network uses group point-wise and depth-wise dilated separable\nconvolutions to learn representations from a large effective receptive field\nwith fewer FLOPs and parameters. The performance of our network is evaluated on\nfour different tasks: (1) object classification, (2) semantic segmentation, (3)\nobject detection, and (4) language modeling. Experiments on these tasks,\nincluding image classification on the ImageNet and language modeling on the\nPenTree bank dataset, demonstrate the superior performance of our method over\nthe state-of-the-art methods. Our network outperforms ESPNet by 4-5% and has\n2-4x fewer FLOPs on the PASCAL VOC and the Cityscapes dataset. Compared to\nYOLOv2 on the MS-COCO object detection, ESPNetv2 delivers 4.4% higher accuracy\nwith 6x fewer FLOPs. Our experiments show that ESPNetv2 is much more power\nefficient than existing state-of-the-art efficient methods including\nShuffleNets and MobileNets. Our code is open-source and available at\nhttps://github.com/sacmehta/ESPNetv2","url_abs":"http://arxiv.org/abs/1811.11431v3","url_pdf":"http://arxiv.org/pdf/1811.11431v3.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":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/sacmehta/EdgeNets","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/ShigemichiMatsuzaki/MSPL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/ikuto056/Estimating_Distance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/justld/EspnetV2_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/oki5656/Estimating_Distance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/sacmehta/espnetv2-coreml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"espnetv2-a-light-weight-power-efficient-and","repo_url":"https://github.com/jonny4929/PaddleSeg_espnetv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cyclical-learning-rate-policy","method_name":"Cyclical Learning Rate Policy"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-dilated-separable-convolution","method_name":"Depthwise Dilated Separable Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"eesp","method_name":"EESP"},{"method_slug":"eru","method_name":"ERU"},{"method_slug":"esp","method_name":"ESP"},{"method_slug":"espnet","method_name":"ESPNet"},{"method_slug":"espnetv2","method_name":"ESPNetv2"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"groupwise-point-convolution","method_name":"Groupwise Point Convolution"},{"method_slug":"hierarchical-feature-fusion","method_name":"Hierarchical Feature Fusion"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"strided-eesp","method_name":"Strided EESP"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"eesp","name":"EESP","full_name":"Extremely Efficient Spatial Pyramid of Depth-wise Dilated Separable Convolutions"},{"slug":"espnetv2","name":"ESPNetv2","full_name":"ESPNetv2"},{"slug":"strided-eesp","name":"Strided EESP","full_name":"Strided EESP"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ESPNetv2","rank_in_archive_order":967,"of":1060,"metrics":{"GFLOPs":"0.602","Number of params":"5.9M","Top 1 Accuracy":"74.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"ESPNetv2","rank_in_archive_order":94,"of":105,"metrics":{"Mean IoU (class)":"66.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"ESPNetv2","rank_in_archive_order":41,"of":51,"metrics":{"Mean IoU":"68.0%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.11431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11431"}},"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/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oki5656/Estimating_Distance","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ikuto056/Estimating_Distance","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/EdgeNets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sacmehta/espnetv2-coreml","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jonny4929/PaddleSeg_espnetv2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/justld/EspnetV2_paddle","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShigemichiMatsuzaki/MSPL","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"43f8cfd6793d23f0","entry":"build_blocks","repo":"zh320/realtime-semantic-segmentation-pytorch","repo_kind":"listed","path":"models/espnetv2.py","file_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch/blob/HEAD/models/espnetv2.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"43f8cfd6793d23f0"}},{"code_sha256_prefix":"2f75a098ce9f7b0e","entry":"partition_list","repo":"jonny4929/PaddleSeg_espnetv2","repo_kind":"listed","path":"paddleseg/core/predict.py","file_url":"https://github.com/jonny4929/PaddleSeg_espnetv2/blob/HEAD/paddleseg/core/predict.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f75a098ce9f7b0e"}},{"code_sha256_prefix":"95bccf5957a196e4","entry":"flip_combination","repo":"jonny4929/PaddleSeg_espnetv2","repo_kind":"listed","path":"paddleseg/core/infer.py","file_url":"https://github.com/jonny4929/PaddleSeg_espnetv2/blob/HEAD/paddleseg/core/infer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"95bccf5957a196e4"}},{"code_sha256_prefix":"026fee631ce4a66c","entry":"get_reverse_list","repo":"jonny4929/PaddleSeg_espnetv2","repo_kind":"listed","path":"paddleseg/core/infer.py","file_url":"https://github.com/jonny4929/PaddleSeg_espnetv2/blob/HEAD/paddleseg/core/infer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"026fee631ce4a66c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}