SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.05967 · 2019

TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1904.05967.json · badge: /api/ran/1904.05967.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ucbdrive/tafe-net canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
weighted_mse_loss Ran
ran, honoured the contract we drafted
ucbdrive/tafe-net/compositional-zs/train_compose.py
code served (permissive licence) · get_code("7e1973afe2913297")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for the weighted_mse_loss function
# input: predicted values, shape (batch_size, dim)
# target: ground truth values, shape (batch_size, dim)
# weight: weights for each element, shape (batch_size, dim)

batch_size = 2
dim = 4

input_tensor = torch.randn(batch_size, dim)
target_tensor = torch.randn(batch_size, dim)
weight_tensor = torch.abs(torch.randn(batch_size, dim)) + 0.1  # ensure positive weights

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
    "weight": weight_tensor,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
validate Not yet run
unverified (harvested, no recorded run)
ucbdrive/tafe-net/compositional-zs/train_compose.py
code served (permissive licence) · get_code("37fcef4cd9c4bcf0")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
ucbdrive/tafe-net/zero-shot/train_zsl.py
code served (permissive licence) · get_code("5bcda5b86b675fe9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learning good feature embeddings for images often requires substantial training data. As a consequence, in settings where training data is limited (e.g., few-shot and zero-shot learning), we are typically forced to use a generic feature embedding across various tasks. Ideally, we want to construct feature embeddings that are tuned for the given task. In this work, we propose Task-Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the image representation to a new task in a meta learning fashion. Our network is composed of a meta learner and a prediction network. Based on a task input, the meta learner generates parameters for the feature layers in the prediction network so that the feature embedding can be accurately adjusted for that task. We show that TAFE-Net is highly effective in generalizing to new tasks or concepts and evaluate the TAFE-Net on a range of benchmarks in zero-shot and few-shot learning. Our model matches or exceeds the state-of-the-art on all tasks. In particular, our approach improves the prediction accuracy of unseen attribute-object pairs by 4 to 15 points on the challenging visual attribute-object composition task.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1904.05967")
get_code_for_paper("1904.05967")
have("1904.05967")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1904.05967.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1904.05967.svg)](https://syntology.ai/paper/1904.05967)

Connect an agent — have() is free.