SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1612.06321 · 2016

Large-Scale Image Retrieval with Attentive Deep Local Features

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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, 2 violated it and 7 have no contract verdict; 3 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/1612.06321.json · badge: /api/ran/1612.06321.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
nashory/DeLF-pytorch community (classifier label)
classifier basis not recorded on the link
12 ran · 0 no recorded run
FunctionStatusWhere it lives
CalculateKeypointCenters Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/delf_helper.py
code served (permissive licence) · get_code("5981d120f5eb39af")
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, 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

torch.manual_seed(0)

# rf_boxes is a [N, 4] FloatTensor representing receptive field boxes
# Each row contains [x_min, y_min, x_max, y_max]
rf_boxes = torch.tensor([
    [10.0, 20.0, 30.0, 40.0],
    [5.0, 15.0, 25.0, 35.0]
], dtype=torch.float32)

ARGS = {
    "rf_boxes": rf_boxes
}
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, 2) — shape (2, 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
CalculateReceptiveBoxes Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/delf_helper.py
code served (permissive licence) · get_code("849ed1ad570b067c")
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 (20, 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)

ARGS = {
    "height": 4,
    "width": 5,
    "rf": 3,
    "stride": 2,
    "padding": 1,
}
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 (20, 4) — shape (20, 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
GenerateCoordinates Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/delf_helper.py
code served (permissive licence) · get_code("5a69d65b6d87d22f")
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 (6, 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

torch.manual_seed(0)

ARGS = {
    "h": 2,
    "w": 3,
}
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 (6, 2) — shape (6, 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
find_classes Ran
ran; our contract draft was wrong, not the code
nashory/DeLF-pytorch/extract/folder.py
code served (permissive licence) · get_code("52d10a10fb72fb9f")
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 a temporary directory with some subdirectories to simulate a class directory structure
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, "class_a"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_b"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "class_c"), exist_ok=True)

ARGS = {
    "dir": temp_dir
}
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
get_inliers Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/matcher.py
code served (permissive licence) · get_code("74aabe4219cf5fe5")
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 numpy as np
from scipy.spatial import cKDTree
from skimage.measure import ransac
from skimage.transform import AffineTransform

# Set random seed for reproducibility
np.random.seed(0)

# Create small feature location arrays (N x 2 for 2D coordinates)
locations_1 = np.array([
    [10.0, 20.0],
    [30.0, 40.0],
    [50.0, 60.0],
    [70.0, 80.0]
], dtype=np.float64)

locations_2 = np.array([
    [12.0, 22.0],
    [32.0, 42.0],
    [52.0, 62.0]
], dtype=np.float64)

# Create small descriptor arrays (N x 4 for 4-dimensional descriptors)
descriptors_1 = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 3.0, 4.0, 5.0],
    [3.0, 4.0, 5.0, 6.0],
    [4.0, 5.0, 6.0, 7.0]
], dtype=np.float64)

descriptors_2 = np.array([
    [1.1, 2.1, 3.1, 4.1],
    [2.1, 3.1, 4.1, 5.1],
    [3.1, 4.1, 5.1, 6.1]
], dtype=np.float64)

ARGS = {
    'locations_1': locations_1,
    'descriptors_1': descriptors_1,
    'locations_2': locations_2,
    'descriptors_2': descriptors_2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, skimage — 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
get_loader Ran
ran on a synthesized input
nashory/DeLF-pytorch/train/dataloader.py
code served (permissive licence) · get_code("7a9dec8d9dfd2eb7")
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 torchvision.transforms as transforms
import torchvision.datasets as datasets
import tempfile
import os
from PIL import Image
import numpy as np

# Create temporary directories with dummy image data
torch.manual_seed(0)

def create_dummy_dataset(path, num_images=4, num_classes=2):
    """Create a dummy ImageFolder dataset structure"""
    os.makedirs(path, exist_ok=True)
    for class_idx in range(num_classes):
        class_dir = os.path.join(path, f"class_{class_idx}")
        os.makedirs(class_dir, exist_ok=True)
        for img_idx in range(num_images):
            # Create a small dummy image (64x64 RGB)
            img_array = np.random.randint(0, 256, (64, 64, 3), dtype=np.uint8)
            img = Image.fromarray(img_array)
            img.save(os.path.join(class_dir, f"image_{img_idx}.jpg"))

# Create temporary directories
train_dir = tempfile.mkdtemp()
val_dir = tempfile.mkdtemp()

# Populate with dummy images
create_dummy_dataset(train_dir, num_images=4, num_classes=2)
create_dummy_dataset(val_dir, num_images=2, num_classes=2)

ARGS = {
    "train_path": train_dir,
    "val_path": val_dir,
    "stage": "finetune",
    "train_batch_size": 2,
    "val_batch_size": 2,
    "sample_size": 64,
    "crop_size": 32,
    "workers": 0,
}
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 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
has_file_allowed_extension Ran
ran, violated the contract we drafted
nashory/DeLF-pytorch/extract/folder.py
code served (permissive licence) · get_code("e800290c5ea55efd")
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 bool, ndim 0, dtype family float, shape () 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.

# Setup code for has_file_allowed_extension

# The function checks if a filename ends with any of the allowed extensions
# filename: a string representing a file path
# extensions: an iterable of extension strings (like ['.jpg', '.png'])

filename = "image.jpg"
extensions = ['.jpg', '.png', '.gif', '.bmp', '.jpeg']

ARGS = {
    'filename': filename,
    'extensions': extensions
}
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 bool, ndim 0, dtype family float, shape () — shape () 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_image_into_numpy_array Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/matcher.py
code served (permissive licence) · get_code("740767f98e8c32bb")
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 ndarray, ndim 3, dtype family int, shape (3, 4, 3) 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.

from PIL import Image
import numpy as np

# Create a test image with RGB mode
img = Image.new('RGB', size=(4, 3), color=(255, 0, 0))

ARGS = {
    'image': img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 4, 3) — shape (3, 4, 3) 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
make_dataset Ran
ran; our contract draft was wrong, not the code
nashory/DeLF-pytorch/extract/folder.py
code served (permissive licence) · get_code("100e7ed2b7d0980f")
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 a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create subdirectories (class folders)
class1_dir = os.path.join(temp_dir, "class1")
class2_dir = os.path.join(temp_dir, "class2")
os.makedirs(class1_dir, exist_ok=True)
os.makedirs(class2_dir, exist_ok=True)

# Create some dummy image files
with open(os.path.join(class1_dir, "image1.jpg"), "w") as f:
    f.write("dummy")
with open(os.path.join(class1_dir, "image2.png"), "w") as f:
    f.write("dummy")
with open(os.path.join(class2_dir, "image3.jpg"), "w") as f:
    f.write("dummy")
with open(os.path.join(class2_dir, "notanimage.txt"), "w") as f:
    f.write("dummy")

# Define the arguments
ARGS = {
    "dir": temp_dir,
    "class_to_idx": {
        "class1": 0,
        "class2": 1
    },
    "extensions": (".jpg", ".jpeg", ".png", ".gif", ".bmp")
}
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
plot_overlap Ran
ran; our contract draft was wrong, not the code
nashory/DeLF-pytorch/utils/logger.py
code served (permissive licence) · get_code("50afa2863ffd9fde")
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 list, 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 matplotlib.pyplot as plt
import numpy as np

class MockLogger:
    def __init__(self):
        self.title = "TestPlot"
        self.names = ["loss", "accuracy", "f1_score"]
        self.numbers = {
            "loss": [0.5, 0.4, 0.3, 0.2],
            "accuracy": [0.7, 0.75, 0.8, 0.85],
            "f1_score": [0.65, 0.72, 0.78, 0.82]
        }

logger = MockLogger()

ARGS = {
    "logger": logger,
    "names": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
read_image Ran
ran on a synthesized input
nashory/DeLF-pytorch/helper/matcher.py
code served (permissive licence) · get_code("69b8e79cea9fed25")
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 ndarray, ndim 3, dtype family int, shape (3, 4, 3) 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 numpy as np
from PIL import Image
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image and save it
img = Image.new('RGB', (4, 3), color=(255, 0, 0))
img.save(temp_image_path)

ARGS = {
    "image_path": temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 4, 3) — shape (3, 4, 3) 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
str2bool Ran
ran, violated the contract we drafted
nashory/DeLF-pytorch/train/config.py
pointer only (licence: MIT); the stored copy get_code serves, from haoran0301/amenunet, is pointer only (licence: NONE) · get_code("248284f69adfeaad")
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 haoran0301/amenunet, 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.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
str2bool 33 other papers
3 dated earlier, 2 the same month, 28 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
and 30 more not named here
plot_overlap 31 other papers
31 later
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1807.09951 (2018-07)
Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
and 28 more not named here
find_classes 30 other papers
1 dated earlier, 29 later
1406.2661 (2014-06)
Generative Adversarial Networks
1809.04729 (2018-09)
A Less Biased Evaluation of Out-of-distribution Sample Detectors
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
and 27 more not named here
has_file_allowed_extension 17 other papers
17 later
1902.02476 (2019-02)
A Simple Baseline for Bayesian Uncertainty in Deep Learning
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
and 14 more not named here
make_dataset 1 other paper
1 later
2002.12186 (2020-02)
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

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

We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature). The new feature is based on convolutional neural networks, which are trained only with image-level annotations on a landmark image dataset. To identify semantically useful local features for image retrieval, we also propose an attention mechanism for keypoint selection, which shares most network layers with the descriptor. This framework can be used for image retrieval as a drop-in replacement for other keypoint detectors and descriptors, enabling more accurate feature matching and geometric verification. Our system produces reliable confidence scores to reject false positives---in particular, it is robust against queries that have no correct match in the database. To evaluate the proposed descriptor, we introduce a new large-scale dataset, referred to as Google-Landmarks dataset, which involves challenges in both database and query such as background clutter, partial occlusion, multiple landmarks, objects in variable scales, etc. We show that DELF outperforms the state-of-the-art global and local descriptors in the large-scale setting by significant margins. Code and dataset can be found at the project webpage: https://github.com/tensorflow/models/tree/master/research/delf .

For agents

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

get_harvested_code_for_paper("1612.06321")
get_code_for_paper("1612.06321")
have("1612.06321")

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

curl https://syntology.ai/api/ran/1612.06321.json

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

[![Syntology run record](https://syntology.ai/api/ran/1612.06321.svg)](https://syntology.ai/paper/1612.06321)

Connect an agent — have() is free.