Papers › Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

22 May 2018arXiv:1805.08402archive 2025-07-28

Tyler R. Scott, Karl Ridgeway, Michael C. Mozer

The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as inductive transfer learning. Three active lines of research have independently explored transfer learning using neural networks. In weight transfer, a model trained on the source domain is used as an initialization point for a network to be trained on the target domain. In deep metric learning, the source domain is used to construct an embedding that captures class structure in both the source and target domains. In few-shot learning, the focus is on generalizing well in the target domain based on a limited number of labeled examples. We compare state-of-the-art methods from these three paradigms and also explore hybrid adapted-embedding methods that use limited target-domain data to fine tune embeddings constructed from source-domain data. We conduct a systematic comparison of methods in a variety of domains, varying the number of labeled instances available in the target domain (k), as well as the number of target-domain classes. We reach three principal conclusions: (1) Deep embeddings are far superior, compared to weight transfer, as a starting point for inter-domain transfer or model re-use (2) Our hybrid methods robustly outperform every few-shot learning and every deep metric learning method previously proposed, with a mean error reduction of 34% over state-of-the-art. (3) Among loss functions for discovering embeddings, the histogram loss (Ustinova & Lempitsky, 2016) is most robust. We hope our results will motivate a unification of research in weight transfer, deep metric learning, and few-shot learning.

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 15 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 6 ran (6 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tylersco/adapted_deep_embeddings officialmentioned in papermentioned on GitHubtfMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
garyCC227/thesis mentioned on GitHubtfMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
1ran · violated contract
11ran
2unverified

Licence: 0 of the 15 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 2 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.

tylersco/adapted_deep_embeddings official repository 9 samples, 7 ran (0 instrument-failed) · 2 unverified
assign_to_device models/utils.py ran MIT (permissive) · 3e5d37390941fbc2 · report fixture: signature device:str/0/str, ps_device:str/0/str · returned function · level recorded 2026-09-25
define_scope models/utils.py ran MIT (permissive) · 6c7c29b9b63f64b3 · report fixture: signature function:callable/0/?, scope:str/0/str, args:tuple/1/empty, kwargs:dict/0/? · returned function · level recorded 2026-09-25
doublewrap models/utils.py ran MIT (permissive) · 4c45b3103c75e41a · report fixture: signature function:callable/0/? · returned function · level recorded 2026-09-25
getDistributionDensity losses/histogram_loss.py ran MIT (permissive) · dcfad983fc978ae3 · report fixture: signature x:EagerTensor/1/float, n:int/0/int, grid:EagerTensor/1/float, grid_delta:float/0/float · returned EagerTensor · level recorded 2026-09-25
hist_loss losses/histogram_loss.py ran MIT (permissive) · 76bdb14f43eeef26 · report fixture: signature z:EagerTensor/2/float, pos_comps:EagerTensor/2/int, n_pos_comps:int/0/int, neg_comps:EagerTensor/2/int, n_neg_comps:int/0/int · returned EagerTensor · level recorded 2026-09-25
max_distances models/recall_at_kappa.py ran MIT (permissive) · 312ded6bde8c5d74 · report fixture: signature X:ndarray/2/float, Y:ndarray/2/float, dist_fun:str/0/str · returned ndarray · level recorded 2026-09-25
prototypical_networks_loss losses/proto_loss.py ran MIT (permissive) · ffbbae661197f477 · report fixture: signature prototypes:EagerTensor/2/float, query:EagerTensor/2/float, num_query_per_class:int/0/int, target_indices:EagerTensor/2/int · returned tuple · level recorded 2026-09-25
classification_batch_evaluation utils.py unverified MIT (permissive) · 17ae2e7840a02242 · report
hist_loss_batch_eval utils.py unverified MIT (permissive) · 0047b13081c4581e · report
garyCC227/thesis community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
create_data in 5 papers model_train.py ran MIT (permissive) · 398f6908e33d3b75 · report fixture: signature images_dict:dict/0/? · returned dict · level recorded 2026-09-26
find_cos_distances models/recall_at_kappa.py ran · violated contract fingerprinted MIT (permissive) · 3b6c6798ddaded17 · report fixture: signature X:ndarray/2/float, Y:ndarray/2/float · returned ndarray · level recorded 2026-09-22
find_l2_distances models/recall_at_kappa.py ran · honoured contract fingerprinted MIT (permissive) · 5ba5211d2daefbb6 · report fixture: signature X:ndarray/2/float, Y:ndarray/2/float · returned ndarray · level recorded 2026-09-22
get_preds in 18 papers dense.py ran fingerprinted MIT (permissive) · feb366896425e713 · report fixture: signature arr:ndarray/2/int · returned ndarray · level recorded 2026-09-26
preprocess_image in 65 papers
census: 4 implementations from 6 papers, 2 distinct outputs on one shared input
dense.py ran MIT (permissive) · 78d8c17e12da6e5d · report fixture: signature image_path:str/0/str, desired_size:int/0/int · returned Image · level recorded 2026-09-26
split_data in 68 papers model_train.py ran MIT (permissive) · 3592b07c9571b601 · report fixture: signature data_dict:dict/0/? · returned tuple · level recorded 2026-09-26

Tasks

Few-Shot LearningMetric LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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