Papers › Colorization as a Proxy Task for Visual Understanding

Colorization as a Proxy Task for Visual Understanding

11 Mar 2017CVPR 2017 7arXiv:1703.04044archive 2025-07-28

Gustav Larsson, Michael Maire, Gregory Shakhnarovich

We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using ImageNet labels for pretraining representations. Moreover, we present the first in-depth analysis of self-supervision via colorization, concluding that formulation of the loss, training details and network architecture play important roles in its effectiveness. This investigation is further expanded by revisiting the ImageNet pretraining paradigm, asking questions such as: How much training data is needed? How many labels are needed? How much do features change when fine-tuned? We relate these questions back to self-supervision by showing that colorization provides a similarly powerful supervisory signal as various flavors of ImageNet pretraining.

PaperPDFConference PDFCodeCode 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 10 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 5 ran (5 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.

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

gustavla/self-supervision officialmentioned in papermentioned on GitHubtfBSD-3-ClauseSyntology: 10 samples, 5 ran (0 instrument-failed) · 5 unverified 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

10 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

5ran
5unverified

Licence: 0 of the 10 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 gustavla/self-supervision. “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.

gustavla/self-supervision official repository 10 samples, 5 ran (0 instrument-failed) · 5 unverified
conv in 178 papers selfsup/jigsaw.py ran BSD-3-Clause (permissive) · a9966f2e69338f0a · report fixture: signature input:EagerTensor/4/float, kernel:EagerTensor/4/float, biases:EagerTensor/1/float, k_h:int/0/int, k_w:int/0/int, c_o:int/0/int, s_h:int/0/int, s_w:int/0/int, padding:str/0/str, group:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-25
conv in 178 papers selfsup/model/alex.py ran BSD-3-Clause (permissive) · 51b2d008e6210eb5 · report fixture: signature input:EagerTensor/4/float, kernel:EagerTensor/4/float, biases:EagerTensor/1/float, k_h:int/0/int, k_w:int/0/int, c_o:int/0/int, s_h:int/0/int, s_w:int/0/int, padding:str/0/str, group:int/0/int · returned EagerTensor · level recorded 2026-09-25
create in 17 papers selfsup/info.py ran BSD-3-Clause (permissive) · 8359957dc18b9b75 · report fixture: signature scale_summary:bool/0/bool · returned dict · level recorded 2026-09-25
leaky_relu in 24 papers selfsup/model/vgg16_bn.py ran BSD-3-Clause (permissive) · e9208491625e9309 · report fixture: signature x:SymbolicTensor/2/float · returned EagerTensor · level recorded 2026-09-25
load_permutations selfsup/jigsaw.py ran BSD-3-Clause (permissive) · 4ca39f8eea1448b8 · report fixture: signature fn:str/0/str · returned ndarray · level recorded 2026-09-25
decode_image in 13 papers selfsup/datasets.py unverified BSD-3-Clause (permissive) · 00c3824b77b7608e · report
init_batch_norm_vars selfsup/model/alex_bn.py unverified BSD-3-Clause (permissive) · 37b8cb185d7de432 · report
moments in 5 papers selfsup/extra.py unverified BSD-3-Clause (permissive) · 26acd189772e5c98 · report
normalize_moments selfsup/extra.py unverified BSD-3-Clause (permissive) · 0b335fc675462059 · report
resize_to_ensure_size selfsup/datasets.py unverified BSD-3-Clause (permissive) · 58bb5de8eea4c169 · report

Tasks

Colorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Colorization

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