SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.02066 · ICCV · 2021

Hierarchical Object-to-Zone Graph for Object Navigation

Weijie Li, Shuqiang Jiang, Sixian Zhang, Xinhang Song, Yubing Bai, Yakui Chu

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 4 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/2109.02066.json · badge: /api/ran/2109.02066.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
sx-zhang/hoz canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
sx-zhang/HOZ community
Papers with Code archive
3 ran · 3 no recorded run
FunctionStatusWhere it lives
ModelOutput Ran
ran on a synthesized input · constructed an object; no result was computed
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("eb772bbf4433bcd4")
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 an instance of its own class, ModelOutput: the run constructed the object and did not call it, so no result was computed. 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 numpy as np

torch.manual_seed(0)

ARGS = {
    "value": torch.tensor([[0.5], [0.3]], dtype=torch.float32),
    "logit": torch.tensor([[1.0, 2.0, 3.0, 4.0], [2.0, 3.0, 4.0, 5.0]], dtype=torch.float32),
    "hidden": torch.tensor([[0.1, 0.2, 0.3, 0.4], [0.5, 0.6, 0.7, 0.8]], dtype=torch.float32),
    "state_representation": torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32),
    "embedding": torch.tensor([[0.2, 0.4, 0.6, 0.8], [0.1, 0.3, 0.5, 0.7]], dtype=torch.float32),
    "state_memory": [torch.tensor([[0.1, 0.2, 0.3, 0.4]]), torch.tensor([[0.5, 0.6, 0.7, 0.8]])],
    "action_memory": [torch.tensor([[1, 2, 3, 4]]), torch.tensor([[5, 6, 7, 8]])],
    "meta_action": torch.tensor([[0, 1, 2, 3], [1, 2, 3, 0]], dtype=torch.int64),
    "visual_info": torch.tensor([[0.9, 0.8, 0.7, 0.6], [0.5, 0.4, 0.3, 0.2]], dtype=torch.float32),
    "obs_rep": torch.tensor([[0.15, 0.25, 0.35, 0.45], [0.55, 0.65, 0.75, 0.85]], dtype=torch.float32),
    "match_score": torch.tensor([[0.95, 0.85], [0.75, 0.65]], dtype=torch.float32),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ModelOutput — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ModelOutput 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
gpuify Ran
ran on a synthesized input
sx-zhang/hoz/utils/model_util.py
code served (permissive licence) · get_code("4f398ddeb57bc2ba")
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 2, dtype family float, shape (2, 4) as a later run recorded it. 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, 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 a small CPU tensor
tensor = torch.randn(2, 4)

# gpu_id: use -1 to avoid actual GPU operations (CPU-only sandbox)
gpu_id = -1

ARGS = {
    "tensor": tensor,
    "gpu_id": gpu_id,
}
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 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
load_scene_graph Ran
ran; our contract draft was wrong, not the code
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("cd8547b18b28a837")
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 scipy.io as scio
import os
import tempfile
import numpy as np

# Create a temporary directory with mock .mat files
temp_dir = tempfile.mkdtemp()

# Create mock .mat files for each scene
scenes = ['Kitchens', 'Living_Rooms', 'Bedrooms', 'Bathrooms']
for scene in scenes:
    # Create a simple mock .mat file with some test data
    mock_data = {
        'nodes': np.array([[1, 2, 3], [4, 5, 6]]),
        'edges': np.array([[0, 1], [1, 0]])
    }
    scio.savemat(os.path.join(temp_dir, scene + '.mat'), mock_data)

ARGS = {
    'path': temp_dir
}
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 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
normalize Ran
ran, honoured the contract we drafted
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("30ac0cb0e95ad225")
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

# The function normalize takes a single parameter x
# It expects x to be a 2D numpy array with numeric values
# The function applies -log transformation, handles zeros, and normalizes non-zero values

# Create a simple 2D numpy array with positive values (needed for log)
x = np.array([
    [0.5, 0.1, 0.0, 0.8],
    [0.2, 0.0, 0.3, 0.9]
], dtype=np.float32)

ARGS = {
    "x": x
}
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
normalize_adj Ran
ran; our contract draft was wrong, not the code
sx-zhang/hoz/models/hoz.py
pointer only (licence: MIT); the stored copy get_code serves, from cassieqiuyd/MJOLNIR, is pointer only (licence: NONE) · get_code("f3a3398f34669aea")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cassieqiuyd/MJOLNIR, 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.

resnet_input_transform Ran
ran on a synthesized input
sx-zhang/hoz/utils/model_util.py
code served (permissive licence) · get_code("63c26f3420b7a699")
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 3, dtype family float, shape (3, 16, 16) 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 numpy as np
from PIL import Image
from torchvision import transforms

torch.manual_seed(0)

class ScaleBothSides(object):
    """Rescales the input PIL.Image to the given 'size'.
    'size' will be the size of both edges, and this can change aspect ratio.
    size: output size of both edges
    interpolation: Default: PIL.Image.BILINEAR
    """

    def __init__(self, size, interpolation=Image.BILINEAR):
        self.size = size
        self.interpolation = interpolation

    def __call__(self, img):
        return img.resize((self.size, self.size), self.interpolation)

def resnet_input_transform(input_image, im_size):
    """Takes in numpy ndarray of size (H, W, 3) and transforms into tensor for
       resnet input.
    """
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    all_transforms = transforms.Compose([transforms.ToPILImage(), ScaleBothSides(im_size), transforms.ToTensor(), normalize])
    transformed_image = all_transforms(input_image)
    return transformed_image

# Create a small numpy ndarray with shape (H, W, 3) for input
input_image = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)

# Create im_size parameter
im_size = 16

ARGS = {
    "input_image": input_image,
    "im_size": im_size
}
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 Tensor, ndim 3, dtype family float, shape (3, 16, 16) — shape (3, 16, 16) 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
toFloatTensor Ran
ran on a synthesized input
sx-zhang/hoz/utils/model_util.py
code served (permissive licence) · get_code("1fc183e5e42354f9")
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 2, dtype family float, shape (2, 4) as a later run recorded it. 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, 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 a small data array
x = [[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]]

# gpu_id of -1 means CPU only (no GPU operations)
gpu_id = -1

ARGS = {
    "x": x,
    "gpu_id": gpu_id,
}
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 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
MetaMemoryHOZ Not yet run
unverified (harvested, no recorded run)
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("e03580641be9da01")
How it ran

no invocation recorded.

dijkstra Not yet run
unverified (harvested, no recorded run)
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("9d3afbea1f937a36")
How it ran

no invocation recorded.

get_value Not yet run
unverified (harvested, no recorded run)
sx-zhang/hoz/gl.py
code served (permissive licence) · get_code("766ee7a843b09775")
How it ran

no invocation recorded.

weights_init Not yet run
unverified (harvested, no recorded run)
sx-zhang/HOZ/models/hoztpn.py
code served (permissive licence) · get_code("f4a41fa606582fdc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 1 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
normalize_adj
brick of this paper's assembly: helper
14 other papers
3 dated earlier, 1 the same month, 10 later
1812.00971 (2018-12)
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
2003.06749 (2020-03)
Learning hierarchical relationships for object-goal navigation
2104.09807 (2021-04)
Visual Navigation with Spatial Attention
and 11 more not named here
gpuify 2 other papers
2 dated earlier
1812.00971 (2018-12)
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
2104.09807 (2021-04)
Visual Navigation with Spatial Attention
resnet_input_transform 2 other papers
2 dated earlier
1812.00971 (2018-12)
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
2104.09807 (2021-04)
Visual Navigation with Spatial Attention
toFloatTensor 2 other papers
2 dated earlier
1812.00971 (2018-12)
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
2104.09807 (2021-04)
Visual Navigation with Spatial Attention
weights_init
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
1602.01783 (2016-02)
Asynchronous Methods for Deep Reinforcement Learning

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

The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an agent to predict actions in real-time. However, in the unseen environment, when the target object is not in egocentric view, the agent may not be able to make wise decisions due to the lack of guidance. In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments. In particular, the HOZ graph is composed of scene nodes, zone nodes and object nodes. With the pre-learned HOZ graph, the real-time observation and the target goal, the agent can constantly plan an optimal path from zone to zone. In the estimated path, the next potential zone is regarded as subgoal, which is also fed into the deep reinforcement learning model for action prediction. Our methods are evaluated on the AI2-Thor simulator. In addition to widely used evaluation metrics SR and SPL, we also propose a new evaluation metric of SAE that focuses on the effective action rate. Experimental results demonstrate the effectiveness and efficiency of our proposed method. The code is available at https://github.com/sx-zhang/HOZ.git.

For agents

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

get_harvested_code_for_paper("2109.02066")
get_code_for_paper("2109.02066")
have("2109.02066")

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

curl https://syntology.ai/api/ran/2109.02066.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.02066.svg)](https://syntology.ai/paper/2109.02066)

Connect an agent — have() is free.