Papers › SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for...

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

4 Dec 2016arXiv:1612.01051archive 2025-07-28

Bichen Wu, Alvin Wan, Forrest Iandola, Peter H. Jin, Kurt Keutzer

Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment. In this work, we propose SqueezeDet, a fully convolutional neural network for object detection that aims to simultaneously satisfy all of the above constraints. In our network, we use convolutional layers not only to extract feature maps but also as the output layer to compute bounding boxes and class probabilities. The detection pipeline of our model only contains a single forward pass of a neural network, thus it is extremely fast. Our model is fully-convolutional, which leads to a small model size and better energy efficiency. While achieving the same accuracy as previous baselines, our model is 30.4x smaller, 19.7x faster, and consumes 35.2x lower energy. The code is open-sourced at https://github.com/BichenWuUCB/squeezeDet.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 30 code samples harvested from 4 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 26 samples from 3 repositories, 18 ran (18 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

BichenWuUCB/squeezeDet officialmentioned in papermentioned on GitHubtfBSD-2-ClauseSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
AjJordy/squeezeDet-master mentioned on GitHubtfBSD-2-ClauseSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
IgorMunizS/mobileDet mentioned on GitHubMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
Yang-YiFan/DiracDeltaNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (arXiv:1807.11164; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
alvinwan/shiftresnet-cifar mentioned on GitHubpytorchSyntology: not harvested report
manikandan-ravikiran/squeezeDet mentioned on GitHubtfBSD-2-ClauseSyntology: not harvested report
nikosRp/Road-Obstacle-Recognition-Using-Images-And-Machine-Learning mentioned on GitHubtfSyntology: not harvested report
omni-us/squeezedet-keras mentioned on GitHubMITSyntology: not harvested report
supernlogn/squeezeDetTL mentioned on GitHubtfMITSyntology: 14 samples, 8 ran (0 instrument-failed) · 6 unverified report
vahidkhosh/squeezeDet mentioned on GitHubtfBSD-2-ClauseSyntology: not harvested report
vahidkhosh/squeezedet-keras mentioned on GitHubMITSyntology: not harvested report
zoeShao/CSC420-Project mentioned on GitHubSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

30 samples harvested: 22 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

22ran
8unverified

Licence: 0 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

BichenWuUCB/squeezeDet official repository 4 samples, 4 ran (0 instrument-failed) · 0 unverified
base_model_config src/config/config.py ran BSD-2-Clause (permissive) · fc8b73ee92df4df4 · report fixture: signature dataset:str/0/str · returned EasyDict · level recorded 2026-09-25
set_anchors src/config/kitti_squeezeDet_config.py ran BSD-2-Clause (permissive) · 9bf0b1a5dd13e9a9 · report fixture: signature mc:MockConfig/0/? · returned ndarray · level recorded 2026-09-25
set_anchors src/config/kitti_res50_config.py ran BSD-2-Clause (permissive) · 53d0d31fe1544ccb · report fixture: signature mc:MockConfig/0/? · returned ndarray · level recorded 2026-09-25
set_anchors src/config/kitti_squeezeDetPlus_config.py ran BSD-2-Clause (permissive) · 583f0b32d683ab52 · report fixture: signature mc:MockConfig/0/? · returned ndarray · level recorded 2026-09-25
AjJordy/squeezeDet-master community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
base_model_config src/config/config.py ran BSD-2-Clause (permissive) · 450ec75dccd80d51 · report fixture: signature dataset:str/0/str · returned EasyDict · level recorded 2026-09-26
set_anchors src/config/ball_config.py ran BSD-2-Clause (permissive) · 6686130be719cf00 · report fixture: signature mc:MockConfig/0/? · returned ndarray · level recorded 2026-09-26
set_anchors src/config/coco_config.py ran BSD-2-Clause (permissive) · 4d4208c08e48b1e7 · report fixture: signature mc:MockConfig/0/? · returned ndarray · level recorded 2026-09-26
IgorMunizS/mobileDet community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
batch_iou main/utils/utils.py ran fingerprinted MIT (permissive) · 258a129e57143728 · report fixture: signature boxes:ndarray/2/float, box:ndarray/1/float · returned ndarray · level recorded 2026-09-26
bbox_transform_single_box main/model/visualization.py ran MIT (permissive) · 9f606fdca1b40bf4 · report fixture: signature bbox:list/1/float · returned list · level recorded 2026-09-26
detachmodel main/model/multi_gpu_model_checkpoint.py ran MIT (permissive) · 498dff14296e4399 · report fixture: signature m:callable/0/? · returned StandInLayer · level recorded 2026-09-26
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
main/utils/utils.py ran fingerprinted MIT (permissive) · 4cdb41e9eb2c173d · report fixture: signature box1:list/1/float, box2:list/1/float · returned float · level recorded 2026-09-26
nms in 65 papers main/utils/utils.py ran MIT (permissive) · 683b91daeb643b9c · report fixture: signature boxes:ndarray/2/float, probs:ndarray/1/float, threshold:float/0/float · returned list · level recorded 2026-09-26
squeezeDet_config main/config/create_config.py ran fingerprinted MIT (permissive) · 225c540640bba3c7 · report fixture: signature name:str/0/str · returned EasyDict · level recorded 2026-09-26
threadsafe_generator main/model/dataGenerator.py ran MIT (permissive) · a51a6cbdf1e527d4 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-26
load_dict in 29 papers main/config/create_config.py unverified MIT (permissive) · 40c1fcd3ded78b67 · report
set_anchors main/config/create_config.py unverified MIT (permissive) · c0ad78591fd23d4e · report
supernlogn/squeezeDetTL community (archive-listed) 14 samples, 8 ran (0 instrument-failed) · 6 unverified
create_mc_from_hopt_vars src/hypervisor/hyperparam_tuner.py ran MIT (permissive) · 0991898b41268d55 · report fixture: signature mc:dict/0/?, hopt_vars_vals:list/1/float, hopt_vars_keys:list/1/str, is_integer:list/1/bool · returned EasyDict · level recorded 2026-09-26
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
src/hypervisor/ga_agent.py ran MIT (permissive) · 4f90612176832908 · report fixture: signature x:ndarray/1/float, mu:ndarray/1/float, sigma:ndarray/1/float · returned ndarray · level recorded 2026-09-26
get_conv2d_out_shape src/config/net_shape_calculator.py ran MIT (permissive) · 290268e740d0a63b · report fixture: signature in_dims:tuple/1/int, filter_sizes:tuple/1/int, strides:tuple/1/int, padding:str/0/str · returned tuple · level recorded 2026-09-26
get_fire_out_shape src/config/net_shape_calculator.py ran MIT (permissive) · ee734fd1d0cab764 · report fixture: signature in_dims:tuple/1/int, s1x1:int/0/int, e1x1:int/0/int, e3x3:int/0/int · returned tuple · level recorded 2026-09-26
get_pool_out_shape src/config/net_shape_calculator.py ran MIT (permissive) · 7a533815750f7bc9 · report fixture: signature in_dims:tuple/1/int, filter_sizes:tuple/1/int, strides:tuple/1/int, padding:str/0/str · returned tuple · level recorded 2026-09-26
get_population_values src/hypervisor/ga_agent.py ran MIT (permissive) · bde67327201e11e5 · report fixture: signature func:callable/0/?, translated_population:list/1/dict, extra_configs:dict/0/? · returned list · level recorded 2026-09-26
get_replaced_contents make_user_compatible.py ran MIT (permissive) · 99dd74c560a09aa5 · report fixture: returned list · level recorded 2026-09-26
translateDNA src/hypervisor/ga_agent.py ran MIT (permissive) · 8dd1b16ef0973cd1 · report fixture: signature pop:ndarray/2/int, var_ranges:dict/0/? · returned list · level recorded 2026-09-26
cook_config src/config/config_cooker.py unverified MIT (permissive) · 4b444fdb9011e9b3 · report
direct_cook_config src/config/config_cooker.py unverified MIT (permissive) · aca95db1ab5ef9f2 · report
get_num_images src/datasets/imdb.py unverified MIT (permissive) · 5dfe260987ce0177 · report
parse_mc src/hypervisor/hyperparam_tuner.py unverified MIT (permissive) · bb34be0fb588c1c8 · report
parse_mc_option src/hypervisor/hyperparam_tuner.py unverified MIT (permissive) · af4f22d25e06d0fc · report
tf_data_augmentation src/datasets/imdb.py unverified MIT (permissive) · a76acdf2ccc4fe25 · report

Tasks

Autonomous DrivingObjectObject DetectionReal-Time Object Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections