SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.00705 · 2020

Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2004.00705.json · badge: /api/ran/2004.00705.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
Tsingularity/PoseNorm_Fewshot canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
proto_eval_k_shot Ran
ran; our contract draft was wrong, not the code
Tsingularity/PoseNorm_Fewshot/utils/models.py
code served (permissive licence) · get_code("4552c641541bef92")
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 1, dtype family int, shape (32,) 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)

# Analyze the function:
# - feature_vector: tensor that gets sliced and reshaped
#   - First way*shot elements become support (way, shot, dim)
#   - Remaining elements become query
#   - The function assumes way*16 query samples (from neg_l2_distance.view(way * 16, way))
# - way: number of classes (int)
# - shot: number of support samples per class (int)
# - dim: feature dimension (int)

# Let's work backwards from the constraints:
# - support = feature_vector[:way * shot].view(way, shot, dim)
# - query = feature_vector[way * shot:].unsqueeze(1)
# - neg_l2_distance has shape (way * 16, way) after view
# - This means query has way * 16 samples
# - So feature_vector needs way*shot + way*16 samples

way = 2
shot = 3
dim = 4

# Total samples needed: way*shot (support) + way*16 (query)
num_support = way * shot  # 2 * 3 = 6
num_query = way * 16      # 2 * 16 = 32
total_samples = num_support + num_query  # 38

# Create feature_vector with shape (total_samples, dim)
feature_vector = torch.randn(total_samples, dim)

ARGS = {
    "feature_vector": feature_vector,
    "way": way,
    "shot": shot,
    "dim": dim,
}
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 1, dtype family int, shape (32,) — shape (32,) 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
proto_forward_log_pred Ran
ran; our contract draft was wrong, not the code
Tsingularity/PoseNorm_Fewshot/utils/models.py
code served (permissive licence) · get_code("4131c9cda4ef30e6")
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 (4, 2) 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.functional as F

torch.manual_seed(0)

# Parameters for proto_forward_log_pred:
# - feature_vector: tensor of shape (way * train_shot + way * test_shot, dim)
# - train_shot: number of support examples per class
# - test_shot: number of query examples per class
# - dim: feature dimension
# - way: number of classes

way = 2
train_shot = 3
test_shot = 2
dim = 4

# Construct feature_vector
# Total size: way * train_shot + way * test_shot = 2*3 + 2*2 = 10 examples
# Shape: (10, 4)
feature_vector = torch.randn(way * train_shot + way * test_shot, dim)

ARGS = {
    "feature_vector": feature_vector,
    "train_shot": train_shot,
    "test_shot": test_shot,
    "dim": dim,
    "way": 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 (4, 2) — shape (4, 2) 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a minimal increase in model capacity, pose normalization improves accuracy between 10 and 20 percentage points for shallow and deep architectures, generalizes better to new domains, and is effective for multiple few-shot algorithms and network backbones. Code is available at https://github.com/Tsingularity/PoseNorm_Fewshot

For agents

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

get_harvested_code_for_paper("2004.00705")
get_code_for_paper("2004.00705")
have("2004.00705")

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

curl https://syntology.ai/api/ran/2004.00705.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.00705.svg)](https://syntology.ai/paper/2004.00705)

Connect an agent — have() is free.