Papers › Deeply-Supervised Nets

Deeply-Supervised Nets

18 Sep 2014arXiv:1409.5185archive 2025-07-28

Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, Zhuowen Tu

Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. We make an attempt to boost the classification performance by studying a new formulation in deep networks. Three aspects in convolutional neural networks (CNN) style architectures are being looked at: (1) transparency of the intermediate layers to the overall classification; (2) discriminativeness and robustness of learned features, especially in the early layers; (3) effectiveness in training due to the presence of the exploding and vanishing gradients. We introduce "companion objective" to the individual hidden layers, in addition to the overall objective at the output layer (a different strategy to layer-wise pre-training). We extend techniques from stochastic gradient methods to analyze our algorithm. The advantage of our method is evident and our experimental result on benchmark datasets shows significant performance gain over existing methods (e.g. all state-of-the-art results on MNIST, CIFAR-10, CIFAR-100, and SVHN).

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1409.5185")

Code

Syntology Ran 0 of 21 code samples harvested from 1 repository linked to this paper; 21 have no recorded run.

By repository: community (archive-listed): 21 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ellisdg/3DUnetCNN mentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

21 samples harvested; 0 ran; 0 honoured the contract we drafted; 21 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

21unverified

Licence: 0 of the 21 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 ellisdg/3DUnetCNN. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

batch_loss ellisdg/3DUnetCNN/unet3d/train/training_utils.py community (archive-listed) unverified MIT (permissive) · e0f6de538e2f1e18 · report
calculate_origin_offset ellisdg/3DUnetCNN/unet3d/utils/affine.py community (archive-listed) unverified MIT (permissive) · 48624962e9942c9f · report
epoch_training ellisdg/3DUnetCNN/unet3d/train/training_utils.py community (archive-listed) unverified MIT (permissive) · d5f1b71fdb23285a · report
epoch_validation ellisdg/3DUnetCNN/unet3d/train/training_utils.py community (archive-listed) unverified MIT (permissive) · c0efd1b82154d3f9 · report
extract_gifti_array ellisdg/3DUnetCNN/unet3d/utils/cifti.py community (archive-listed) unverified MIT (permissive) · d7f84b2efefc9200 · report
extract_gifti_array_names ellisdg/3DUnetCNN/unet3d/utils/cifti.py community (archive-listed) unverified MIT (permissive) · a613b779df9b18fb · report
extract_gifti_surface_vertices ellisdg/3DUnetCNN/unet3d/utils/cifti.py community (archive-listed) unverified MIT (permissive) · ec8a60718108f746 · report
flip_image ellisdg/3DUnetCNN/unet3d/utils/augment.py community (archive-listed) unverified MIT (permissive) · e3f4fafafb4fd349 · report
generate_hcp_filenames ellisdg/3DUnetCNN/unet3d/utils/filenames.py community (archive-listed) unverified MIT (permissive) · e6578b6b8b776391 · report
get_feature_filename_and_subject_id ellisdg/3DUnetCNN/unet3d/predict/utils.py community (archive-listed) unverified MIT (permissive) · 6db950092e32b901 · report
get_image ellisdg/3DUnetCNN/unet3d/utils/image.py community (archive-listed) unverified MIT (permissive) · 50a36c3ef53a39bf · report
get_spacing_from_affine ellisdg/3DUnetCNN/unet3d/utils/affine.py community (archive-listed) unverified MIT (permissive) · ac1b3032b0af0eeb · report
infer_subject_id ellisdg/3DUnetCNN/unet3d/predict/utils.py community (archive-listed) unverified MIT (permissive) · 7855782a9942e2e4 · report
load_images_from_dataset ellisdg/3DUnetCNN/unet3d/predict/volumetric.py community (archive-listed) unverified MIT (permissive) · d175ff824428b980 · report
load_state_dict ellisdg/3DUnetCNN/unet3d/models/build.py community (archive-listed) unverified MIT (permissive) · fb1d0885dc8670c6 · report
load_volumetric_model ellisdg/3DUnetCNN/unet3d/predict/volumetric.py community (archive-listed) unverified MIT (permissive) · a952576fb1f2c26a · report
pytorch_predict_batch_array ellisdg/3DUnetCNN/unet3d/predict/utils.py community (archive-listed) unverified MIT (permissive) · 0a4754cb9d311c12 · report
random_flip_dimensions ellisdg/3DUnetCNN/unet3d/utils/augment.py community (archive-listed) unverified MIT (permissive) · 360dfc67628c771e · report
random_scale_factor ellisdg/3DUnetCNN/unet3d/utils/augment.py community (archive-listed) unverified MIT (permissive) · c746ac1567201dd2 · report
set_affine_spacing ellisdg/3DUnetCNN/unet3d/utils/affine.py community (archive-listed) unverified MIT (permissive) · aed17f756b9cc8c3 · report
wrapped_partial ellisdg/3DUnetCNN/unet3d/utils/filenames.py community (archive-listed) unverified MIT (permissive) · 1e0de6b9c650bc32 · report

Tasks

ClassificationGeneral ClassificationImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 DSN Percentage correct 91.8 #188 of 265 Archive leaderboard report
Image Classification CIFAR-100 DSN Percentage correct 65.4 #192 of 211 Archive leaderboard report
Image Classification MNIST DSN Percentage error 0.4 #24 of 81 Archive leaderboard report
Image Classification SVHN DSN Percentage error 1.9 #25 of 62 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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