SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09510 · ECCV · 2022

Contributions of Shape, Texture, and Color in Visual Recognition

Zhi Xu, Yunhao Ge, Laurent Itti, Xingrui Wang, Yao Xiao

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 3 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/2207.09510.json · badge: /api/ran/2207.09510.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
gyhandy/humanoid-vision-engine canonical (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
FunctionStatusWhere it lives
adaptive_instance_normalization Ran
ran; our contract draft was wrong, not the code
gyhandy/humanoid-vision-engine/Imagine/models.py
code served (permissive licence) · get_code("16679a24b9881031")
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 4, dtype family float, shape (2, 4, 3, 5) 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 4D tensors for content and style features
# Shape: (N, C, H, W) where N=batch, C=channels, H=height, W=width
# Using distinct sizes: batch=2, channels=4, height=3, width=5
content_feat = torch.randn(2, 4, 3, 5)
style_feat = torch.randn(2, 4, 3, 5)

ARGS = {
    "content_feat": content_feat,
    "style_feat": style_feat,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
calc_mean_std Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gyhandy/humanoid-vision-engine/Imagine/models.py
code served (permissive licence) · get_code("38eaf8511dc7bc9c")
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 tuple, ndim 5, 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)

# The function expects a 4D tensor (N, C, H, W)
# N = batch size, C = channels, H = height, W = width
# Using distinct sizes: batch=2, channels=4, height=3, width=5
feat = torch.randn(2, 4, 3, 5)

ARGS = {
    "feat": feat,
    "eps": 1e-05
}
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 tuple, ndim 5, 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_modality_Dataloader Ran
ran on a synthesized input
gyhandy/humanoid-vision-engine/Zero_shot/data_loader_modality.py
code served (permissive licence) · get_code("82c9ace65355539f")
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 DataLoader. 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 os
import tempfile
from PIL import Image
import torch.nn as nn

torch.manual_seed(0)

# Create temporary directories with minimal structure
temp_dir = tempfile.mkdtemp()
root_shape = os.path.join(temp_dir, "shape")
root_texture = os.path.join(temp_dir, "texture")
root_color = os.path.join(temp_dir, "color")

for root in [root_shape, root_texture, root_color]:
    os.makedirs(root, exist_ok=True)

# Create minimal class directories and image files
class_names = ["class_a", "class_b"]
for class_name in class_names:
    for root in [root_shape, root_texture, root_color]:
        os.makedirs(os.path.join(root, class_name), exist_ok=True)
    
    # Create 2 sample images per class
    for i in range(2):
        # Texture images (JPEG)
        img_name = f"{class_name}_img{i}.JPEG"
        img = Image.new('RGB', (100, 100), color='red')
        img.save(os.path.join(root_texture, class_name, img_name))
        
        # Shape images (PNG)
        img_name_png = f"{class_name}_img{i}.png"
        img = Image.new('RGB', (100, 100), color='blue')
        img.save(os.path.join(root_shape, class_name, img_name_png))
        
        # Color images (JPG)
        img_name_jpg = f"{class_name}_img{i}.jpg"
        img = Image.new('RGB', (100, 100), color='green')
        img.save(os.path.join(root_color, class_name, img_name_jpg))

ARGS = {
    "root_shape": root_shape,
    "root_texture": root_texture,
    "root_color": root_color,
    "batch_size": 2,
    "shuffle": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
get_retrival_Dataloader Ran
ran on a synthesized input
gyhandy/humanoid-vision-engine/Zero_shot/data_loader_modality.py
code served (permissive licence) · get_code("134aa92d49baf521")
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 DataLoader. 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 os
import tempfile
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create temporary directories with minimal structure
temp_dir = tempfile.mkdtemp()
root_shape = os.path.join(temp_dir, 'shape')
root_texture = os.path.join(temp_dir, 'texture')
root_color = os.path.join(temp_dir, 'color')

for root in [root_shape, root_texture, root_color]:
    os.makedirs(root, exist_ok=True)

# Create minimal class directories and image files
class_dirs = ['class_A', 'class_B']
for class_dir in class_dirs:
    for root in [root_shape, root_texture, root_color]:
        os.makedirs(os.path.join(root, class_dir), exist_ok=True)
    
    # Create 3 sample images per class
    for i in range(3):
        # Texture images (JPEG)
        img_name = f"{class_dir}_img{i}.jpg"
        img = Image.new('RGB', (32, 32), color=(73, 109, 137))
        img.save(os.path.join(root_texture, class_dir, img_name))
        
        # Shape images (PNG)
        img_name_shape = f"{class_dir}_img{i}.png"
        img = Image.new('RGB', (32, 32), color=(100, 120, 140))
        img.save(os.path.join(root_shape, class_dir, img_name_shape))
        
        # Color images (JPG)
        img_name_color = f"{class_dir}_img{i}.jpg"
        img = Image.new('RGB', (32, 32), color=(150, 160, 170))
        img.save(os.path.join(root_color, class_dir, img_name_color))

ARGS = {
    'root_shape': root_shape,
    'root_texture': root_texture,
    'root_color': root_color,
    'batch_size': 2,
    'shuffle': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
record_acc Ran
ran on a synthesized input
gyhandy/humanoid-vision-engine/Zero_shot/cross_modality_two_latents.py
code served (permissive licence) · get_code("961a212d9dfa61b4")
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 2, dtype family int; no output shape is stated. 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 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

torch.manual_seed(0)

# The function expects:
# - pre: a tensor with logits/predictions that can be passed to torch.max(..., 1)
# - label: a tensor with class labels
# - total: a list that stores total counts per class
# - correct: a list that stores correct counts per class
# - class_num: an integer specifying number of classes

# Create small tensors
batch_size = 2
num_classes = 4
output_dim = 3

# pre: prediction tensor with shape (batch_size, num_classes)
# torch.max will select the class with highest score
pre = torch.randn(batch_size, num_classes)

# label: ground truth class indices, shape (batch_size,)
label = torch.tensor([0, 2])

# total and correct: lists to accumulate statistics
# Index 0 stores overall total/correct, indices 1..class_num-1 store per-class stats
total = [0] * num_classes
correct = [0] * num_classes

# class_num: number of classes
class_num = num_classes

ARGS = {
    "pre": pre,
    "label": label,
    "total": total,
    "correct": correct,
    "class_num": class_num
}
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 2, dtype family int — 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_concept_latent Not yet run
unverified (harvested, no recorded run)
gyhandy/humanoid-vision-engine/Zero_shot/cross_modality_two_latents.py
code served (permissive licence) · get_code("8aa906b9bc724932")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
gyhandy/humanoid-vision-engine/HNN/compute_bias.py
code served (permissive licence) · get_code("883ccd49b57f68c5")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
gyhandy/humanoid-vision-engine/Zero_shot/cross_modality_two_latents.py
code served (permissive licence) · get_code("e6fe8a84c5113f3c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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
calc_mean_std 26 other papers
14 dated earlier, 9 later, 3 same year, order not determinable · 4 only as an assembly brick
1703.06868 (2017-03)
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
1812.02342 (2018-12)
Arbitrary Style Transfer with Style-Attentional Networks
1911.10033 (2019-11)
Domain Adaptation for Object Detection via Style Consistency
and 23 more not named here
adaptive_instance_normalization 12 other papers
8 dated earlier, 3 later, 1 same year, order not determinable
1703.06868 (2017-03)
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
1911.10033 (2019-11)
Domain Adaptation for Object Detection via Style Consistency
2003.08436 (2020-03)
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
and 9 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

We investigate the contributions of three important features of the human visual system (HVS) -shape, texture, and color -to object classification. We build a humanoid vision engine (HVE) that explicitly and separately computes shape, texture, and color features from images. The resulting feature vectors are then concatenated to support the final classification. We show that HVE can summarize and rankorder the contributions of the three features to object recognition. We use human experiments to confirm that both HVE and humans predominantly use some specific features to support the classification of specific classes (e.g., texture is the dominant feature to distinguish a zebra from other quadrupeds, both for humans and HVE). With the help of HVE, given any environment (dataset), we can summarize the most important features for the whole task (task-specific; e.g., color is the most important feature overall for classification with the CUB dataset), and for each class (class-specific; e.g., shape is the most important feature to recognize boats in the iLab-20M dataset). To demonstrate more usefulness of HVE, we use it to simulate the open-world zero-shot learning ability of humans with no attribute labeling. Finally, we show that HVE can also simulate human imagination ability with the combination of different features.

For agents

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

get_harvested_code_for_paper("2207.09510")
get_code_for_paper("2207.09510")
have("2207.09510")

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

curl https://syntology.ai/api/ran/2207.09510.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.09510.svg)](https://syntology.ai/paper/2207.09510)

Connect an agent — have() is free.