SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.00839 · 2018

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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 6 have no contract verdict; 7 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/1803.00839.json · badge: /api/ran/1803.00839.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
penincillin/DREAM community (classifier label)
classifier basis not recorded on the link
13 ran · 2 no recorded run
FunctionStatusWhere it lives
calc_eer Ran
ran on a synthesized input
penincillin/DREAM/src/CFP/eval_roc.py
code served (permissive licence) · get_code("6edef450883b178e")
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 float64, ndim 0, 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 numpy as np
from scipy.optimize import fsolve

# Construct valid arguments for calc_eer function
# The function takes fpr (false positive rate), tpr (true positive rate), and method

# Create sample FPR and TPR arrays
# These should be monotonically increasing arrays representing ROC curve points
fpr = np.array([0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9])
tpr = np.array([0.0, 0.15, 0.35, 0.55, 0.7, 0.8, 0.85, 0.88, 0.92, 0.95])

# Define ARGS dictionary with all parameters
ARGS = {
    "fpr": fpr,
    "tpr": tpr,
    "method": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
conv3x3 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/CFP/ResNet.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

eval_roc Ran
ran on a synthesized input
penincillin/DREAM/src/CFP/eval_roc.py
code served (permissive licence) · get_code("8dc8afb9def7beab")
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 numpy as np
import tempfile
import os

# Create temporary directory structure for protocol files
temp_dir = tempfile.mkdtemp()
protocol_dir = temp_dir

# Create directory structure
for pair_type in ['FF', 'FP']:
    for split_name in ['test']:
        dir_path = os.path.join(protocol_dir, pair_type, split_name)
        os.makedirs(dir_path, exist_ok=True)

# Create sample pair files
# diff.txt - different people (label 0)
diff_content = """1,2
2,3
3,4
4,5"""

same_content = """1,1
2,2
3,3
4,4"""

for pair_type in ['FF', 'FP']:
    for split_name in ['test']:
        diff_file = os.path.join(protocol_dir, pair_type, split_name, 'diff.txt')
        same_file = os.path.join(protocol_dir, pair_type, split_name, 'same.txt')
        
        with open(diff_file, 'w') as f:
            f.write(diff_content)
        
        with open(same_file, 'w') as f:
            f.write(same_content)

# Create feature vectors (normalized for cosine similarity)
np.random.seed(0)
num_subjects = 5
feature_dim = 128

frontal_feats = []
for i in range(num_subjects):
    feat = np.random.randn(feature_dim).astype(np.float32)
    feat = feat / np.linalg.norm(feat)  # normalize
    frontal_feats.append(feat)

profile_feats = []
for i in range(num_subjects):
    feat = np.random.randn(feature_dim).astype(np.float32)
    feat = feat / np.linalg.norm(feat)  # normalize
    profile_feats.append(feat)

ARGS = {
    'protocol_dir': protocol_dir,
    'pair_type': 'FF',
    'split_name': 'test',
    'frontal_feats': frontal_feats,
    'profile_feats': profile_feats
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — 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
get_dict Ran
ran on a synthesized input
penincillin/DREAM/src/stitching/branch_train.py
code served (permissive licence) · get_code("76c04a1779da3515")
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 dict. The image it ran in was 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 tempfile
import os

# Create a temporary file with test data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file_name = temp_file.name

# Write test data to the file
# Format: img_name yaw
test_data = [
    "celeb1/image1.jpg 15.0",
    "celeb1/image2.jpg 55.0",
    "celeb1/image3.jpg 18.0",
    "celeb1/image4.jpg 60.0",
    "celeb2/image5.jpg 10.0",
    "celeb2/image6.jpg 52.0",
    "celeb2/image7.jpg 12.0",
    "celeb2/image8.jpg 65.0",
    "celeb3/image9.jpg 25.0",
]

for line in test_data:
    temp_file.write(line + "\n")

temp_file.close()

ARGS = {
    "file_name": temp_file_name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
load_feat Ran
ran on a synthesized input
penincillin/DREAM/src/CFP/eval_roc.py
code served (permissive licence) · get_code("e53e7c8483ea523a")
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 list, 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 numpy as np
import struct as st
import tempfile
import os

# Create a temporary binary file with the expected format
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.bin')
temp_path = temp_file.name

try:
    # Write feature data in the format expected by load_feat
    feat_num = 3
    feat_dim = 4
    
    # Pack header: feature count and dimension
    temp_file.write(st.pack('ii', feat_num, feat_dim))
    
    # Write feature vectors
    for i in range(feat_num):
        feat_vector = [float(j + i) for j in range(feat_dim)]
        temp_file.write(st.pack('f' * feat_dim, *feat_vector))
    
    temp_file.close()
    
    ARGS = {
        'feat_file': temp_path
    }
finally:
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
load_imgs Ran
ran on a synthesized input
penincillin/DREAM/src/CFP/selfDefine.py
code served (permissive licence) · get_code("0e2356a2cc760d35")
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 list, 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 os
import tempfile
import shutil

# Create temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
img_dir = os.path.join(temp_dir, "images")
os.makedirs(img_dir, exist_ok=True)

# Create a temporary image list file
image_list_file = os.path.join(temp_dir, "image_list.txt")
with open(image_list_file, 'w') as f:
    f.write("img1.jpg 45.5\n")
    f.write("img2.jpg 90.0\n")
    f.write("img3.jpg 135.3\n")

# Create dummy image files
for i in range(1, 4):
    img_path = os.path.join(img_dir, f"img{i}.jpg")
    with open(img_path, 'w') as f:
        f.write(f"dummy image {i}")

ARGS = {
    "img_dir": img_dir,
    "image_list_file": image_list_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
load_imgs Ran
ran on a synthesized input
penincillin/DREAM/src/end2end/selfDefine.py
code served (permissive licence) · get_code("6f8560ba80c4fa6e")
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. The image it ran in was 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 os
import tempfile
import shutil

# Create temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
img_dir = os.path.join(temp_dir, "images")
os.makedirs(img_dir, exist_ok=True)

# Create dummy image files
for i in range(3):
    open(os.path.join(img_dir, f"img_{i}.jpg"), 'w').close()

# Create image list file
image_list_file = os.path.join(temp_dir, "image_list.txt")
with open(image_list_file, 'w') as f:
    f.write("img_0.jpg\n")
    f.write("img_1.jpg\n")
    f.write("img_2.jpg\n")

# Create label file
label_file = os.path.join(temp_dir, "labels.txt")
with open(label_file, 'w') as f:
    # First line: total_num label_num
    f.write("3 2\n")
    # Subsequent lines: label yaw
    f.write("0 15.5\n")
    f.write("1 -30.2\n")
    f.write("0 45.1\n")

ARGS = {
    "img_dir": img_dir,
    "image_list_file": image_list_file,
    "label_file": label_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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: none by the harness; any seed is in the setup block
resnet18 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/CFP/ResNet.py
code served (permissive licence) · get_code("fc7697ccba1dfe96")
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 ResNet. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
resnet18 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/IJBA/ResNet.py
code served (permissive licence) · get_code("abc2b710282f3b3f")
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 ResNet. The image it ran in was 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 torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
resnet18 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/end2end/ResNet.py
code served (permissive licence) · get_code("16fb1b03af4952ef")
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 ResNet. The image it ran in was 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
resnet34 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/CFP/ResNet.py
code served (permissive licence) · get_code("e670ddb9c9a43661")
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 ResNet. The image it ran in was 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
resnet34 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/IJBA/ResNet.py
code served (permissive licence) · get_code("bafccd9145f43de0")
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 ResNet. The image it ran in was 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
resnet34 Ran
ran; our contract draft was wrong, not the code
penincillin/DREAM/src/end2end/ResNet.py
code served (permissive licence) · get_code("321f5f251cf53205")
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 ResNet. The image it ran in was 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
gen_batch Not yet run
unverified (harvested, no recorded run)
penincillin/DREAM/src/stitching/branch_train.py
code served (permissive licence) · get_code("1dc8a5fafca11ad9")
How it ran

no invocation recorded.

get_idle_gpu Not yet run
unverified (harvested, no recorded run)
penincillin/DREAM/src/end2end/slurm.py
code served (permissive licence) · get_code("68b0020055f92a8d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 8 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
37 dated earlier, 8 the same month, 641 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
2 dated earlier, 1 the same month, 86 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.08494 (2018-03)
Group Normalization
and 86 more not named here
resnet34 53 other papers
2 dated earlier, 1 the same month, 50 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.08494 (2018-03)
Group Normalization
and 50 more not named here

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

Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead.

For agents

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

get_harvested_code_for_paper("1803.00839")
get_code_for_paper("1803.00839")
have("1803.00839")

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

curl https://syntology.ai/api/ran/1803.00839.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.00839.svg)](https://syntology.ai/paper/1803.00839)

Connect an agent — have() is free.