SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.06315 · ICCV · 2023

DETA: Denoised Task Adaptation for Few-Shot Learning

Xu Luo, Jingkuan Song, Lianli Gao, Ji Zhang, Hengtao Shen

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 3 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/2303.06315.json · badge: /api/ran/2303.06315.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
JimZAI/DETA community
Papers with Code archive
4 ran · 3 no recorded run
FunctionStatusWhere it lives
SupCluLoss Ran
ran on a synthesized input
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("b9ecf342c8a429fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type 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 numpy as np

INIT_ARGS = {
    'temperature': 0.3,
    'contrast_mode': 'all',
    'base_temperature': 0.07
}

# Create synthetic data
batch_size = 2
feature_dim = 4
num_classes = 2
K_patch = 3
way = 2
shot_nums = [1, 1]  # Two classes, 1 shot each

# Features: batch_size x feature_dim
features = torch.randn(batch_size * K_patch, feature_dim)

# Labels: batch_size x 1
labels = torch.tensor([0] * K_patch + [1] * K_patch, dtype=torch.long).view(-1, 1)

# Query embeddings (for patch weighting)
q_emb_dim = 4
q_emb = torch.randn(batch_size * K_patch, q_emb_dim)

ARGS = {
    'features': features,
    'labels': labels,
    'shot_nums': shot_nums,
    'is_weight_patch': True,
    'q_emb': q_emb,
    'K_patch': K_patch
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
compute_prototypes Ran
ran; our contract draft was wrong, not the code
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("a4c757e9b96b1bd8")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Create small embeddings tensor: shape (batch_size=2, embedding_dim=4)
embeddings = torch.randn(2, 4, dtype=torch.float32)

# Create labels tensor: shape (batch_size=2,) with values in range [0, n_way)
# For n_way=2, labels should be [0, 1]
labels = torch.tensor([0, 1], dtype=torch.long)

# Number of ways (classes)
n_way = 2

ARGS = {
    "embeddings": embeddings,
    "labels": labels,
    "n_way": n_way,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
projector Ran
ran on a synthesized input
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("5f57cfcaa92a7158")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# INIT_ARGS for projector.__init__
INIT_ARGS = {
    'z_dim': 8,
    'feat_dim': 12,
    'type': 'mlp'
}

# ARGS for projector.forward
ARGS = {
    'x': torch.randn(2, 12)  # batch_size=2, feat_dim=12 (must match INIT_ARGS['feat_dim'])
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
prototype_loss Ran
ran; our contract draft was wrong, not the code
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("dbb8ef5cff4f0915")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tiny support embeddings: 6 samples, 4-dimensional embeddings
support_embeddings = torch.randn(6, 4)

# Create support labels: 3-way classification, 2 samples per class
support_labels = torch.tensor([0, 0, 1, 1, 2, 2])

# Create tiny query embeddings: 4 samples, 4-dimensional embeddings
query_embeddings = torch.randn(4, 4)

# Create query labels: 3-way classification
query_labels = torch.tensor([0, 1, 2, 0])

# Create patch_weight as a 4x3 tensor (4 query samples, 3 ways)
patch_weight = torch.ones(4, 3)

ARGS = {
    'support_embeddings': support_embeddings,
    'support_labels': support_labels,
    'query_embeddings': query_embeddings,
    'query_labels': query_labels,
    'patch_weight': patch_weight,
    'distance': 'cos'
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
gen_patches_tensor Not yet run
unverified (harvested, no recorded run)
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("031209dda35f6e6d")
How it ran

no invocation recorded.

resize_transform_tensor Not yet run
unverified (harvested, no recorded run)
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("ee9301c5b04bdf40")
How it ran

no invocation recorded.

ta Not yet run
unverified (harvested, no recorded run)
JimZAI/DETA/models/ta.py
code served (permissive licence) · get_code("dbcd4f4c39c55f25")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on developing advanced algorithms to achieve the goal, while neglecting the inherent problems of the given support samples. In fact, with only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified. To address this challenge, in this work we propose DEnoised Task Adaptation (DETA), a first, unified image-and label-denoising framework orthogonal to existing task adaptation approaches. Without extra supervision, DETA filters out task-irrelevant, noisy representations by taking advantage of both global visual information and local region details of support samples. On the challenging Meta-Dataset, DETA consistently improves the performance of a broad spectrum of baseline methods applied on various pre-trained models. Notably, by tackling the overlooked image noise in Meta-Dataset, DETA establishes new state-of-the-art results. Code is released at https://github.com/JimZAI/DETA.

For agents

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

get_harvested_code_for_paper("2303.06315")
get_code_for_paper("2303.06315")
have("2303.06315")

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

curl https://syntology.ai/api/ran/2303.06315.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.06315.svg)](https://syntology.ai/paper/2303.06315)

Connect an agent — have() is free.