{"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/deep-learning-with-low-precision-by-half-wave","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","arxiv_id":"1702.00953","date":"2017-02-03","proceeding":"CVPR 2017 7","authors":["Zhaowei Cai","Xiaodong He","Jian Sun","Nuno Vasconcelos"],"abstract":"The problem of quantizing the activations of a deep neural network is\nconsidered. An examination of the popular binary quantization approach shows\nthat this consists of approximating a classical non-linearity, the hyperbolic\ntangent, by two functions: a piecewise constant sign function, which is used in\nfeedforward network computations, and a piecewise linear hard tanh function,\nused in the backpropagation step during network learning. The problem of\napproximating the ReLU non-linearity, widely used in the recent deep learning\nliterature, is then considered. An half-wave Gaussian quantizer (HWGQ) is\nproposed for forward approximation and shown to have efficient implementation,\nby exploiting the statistics of of network activations and batch normalization\noperations commonly used in the literature. To overcome the problem of gradient\nmismatch, due to the use of different forward and backward approximations,\nseveral piece-wise backward approximators are then investigated. The\nimplementation of the resulting quantized network, denoted as HWGQ-Net, is\nshown to achieve much closer performance to full precision networks, such as\nAlexNet, ResNet, GoogLeNet and VGG-Net, than previously available low-precision\nnetworks, with 1-bit binary weights and 2-bit quantized activations.","url_abs":"http://arxiv.org/abs/1702.00953v1","url_pdf":"http://arxiv.org/pdf/1702.00953v1.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":"deep-learning-with-low-precision-by-half-wave","repo_url":"https://github.com/zhaoweicai/hwgq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"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":"convolution","method_name":"Convolution"},{"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":"googlenet","method_name":"GoogLeNet"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.00953","atlas_url":"https://app.syntology.ai/?focus=1702.00953","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":"1702.00953"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.00953\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.00953"},"call":"get_concepts_for_paper(arxiv_id=\"1702.00953\")"}],"by_repo":[{"repo":"zhaoweicai/hwgq","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":"bd2a59302afda9bb1d3dc70c42603f12d8c299c57fac9c3393aed90a43bd132b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}