SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.03342 · 2018

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 1 failure 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/1807.03342.json · badge: /api/ran/1807.03342.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
ppengtang/oicr canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
bbox_transform Ran
ran, violated the contract we drafted
ppengtang/oicr/lib/fast_rcnn/bbox_transform.py
code served (permissive licence) · get_code("84dcf978d5570762")
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 2, dtype family float, shape (2, 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 numpy as np

# bbox_transform expects two numpy arrays of bounding boxes
# Each bbox is [x1, y1, x2, y2] format
# The function computes regression targets from example rois to ground truth rois

# Create small example ROIs (batch of 2 boxes, 4 coords each)
ex_rois = np.array([
    [10.0, 20.0, 50.0, 80.0],
    [5.0, 15.0, 45.0, 75.0]
], dtype=np.float32)

# Create small ground truth ROIs (batch of 2 boxes, 4 coords each)
gt_rois = np.array([
    [12.0, 22.0, 52.0, 82.0],
    [7.0, 17.0, 47.0, 77.0]
], dtype=np.float32)

ARGS = {
    "ex_rois": ex_rois,
    "gt_rois": gt_rois
}
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 ndarray, 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
bbox_transform_inv Ran
ran, honoured the contract we drafted
ppengtang/oicr/lib/fast_rcnn/bbox_transform.py
code served (permissive licence) · get_code("b3695ebe0c382b05")
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 2, dtype family float, shape (2, 8) 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

# Create small test data for bbox_transform_inv
# boxes: N x 4 array of bounding boxes [x1, y1, x2, y2]
# deltas: N x (4*K) array of box deltas for K classes

boxes = np.array([
    [10.0, 20.0, 50.0, 80.0],
    [100.0, 150.0, 200.0, 250.0]
], dtype=np.float32)

# deltas: 2 boxes, 2 classes (8 columns: dx, dy, dw, dh for each class)
deltas = np.array([
    [0.1, 0.2, -0.1, 0.05, 0.15, 0.1, -0.2, 0.0],
    [-0.05, 0.0, 0.1, -0.1, 0.2, -0.15, 0.05, 0.1]
], dtype=np.float32)

ARGS = {
    "boxes": boxes,
    "deltas": deltas
}
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 ndarray, ndim 2, dtype family float, shape (2, 8) — shape (2, 8) 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
clip_boxes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ppengtang/oicr/lib/fast_rcnn/bbox_transform.py
code served (permissive licence) · get_code("d24c99284beca7a6")
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 2, dtype family float, shape (2, 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 numpy as np

# Create sample boxes array
# Shape: (num_boxes, num_coords) where coords are in format [x1, y1, x2, y2, ...]
# Using 2 boxes with 4 coordinates each (x1, y1, x2, y2)
boxes = np.array([
    [10.5, 20.3, 100.7, 150.2],
    [5.1, 15.8, 200.4, 300.9]
], dtype=np.float32)

# Image shape as (height, width)
im_shape = (256, 512)

ARGS = {
    "boxes": boxes,
    "im_shape": im_shape
}
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 ndarray, 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
prep_im_for_blob Ran
ran on a synthesized input
ppengtang/oicr/lib/utils/blob.py
code served (permissive licence) · get_code("9fa9d06d239312ea")
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
import cv2

# Create a simple test image (height=480, width=640, channels=3)
im = np.random.randint(0, 256, size=(480, 640, 3), dtype=np.uint8)

# Define pixel means for normalization (typically BGR means)
pixel_means = np.array([103.939, 116.779, 123.68], dtype=np.float32)

# Target size for the smaller dimension
target_size = 600

# Maximum size for the larger dimension
max_size = 1000

ARGS = {
    "im": im,
    "pixel_means": pixel_means,
    "target_size": target_size,
    "max_size": max_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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_imdb Not yet run
unverified (harvested, no recorded run)
ppengtang/oicr/lib/datasets/factory.py
code served (permissive licence) · get_code("9f3cea1708a8a9db")
How it ran

no invocation recorded.

get_output_dir Not yet run
unverified (harvested, no recorded run)
ppengtang/oicr/lib/fast_rcnn/config.py
code served (permissive licence) · get_code("b0dcfe8273d808a7")
How it ran

no invocation recorded.

im_list_to_blob Not yet run
unverified (harvested, no recorded run)
ppengtang/oicr/lib/utils/blob.py
code served (permissive licence) · get_code("015af0d600124541")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
clip_boxes 7 other papers
7 dated earlier
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1506.02025 (2015-06)
Spatial Transformer Networks
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
and 4 more not named here
bbox_transform 4 other papers
4 dated earlier
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1506.02025 (2015-06)
Spatial Transformer Networks
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
and 1 more not named here
bbox_transform_inv 4 other papers
4 dated earlier
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1506.02025 (2015-06)
Spatial Transformer Networks
1612.03144 (2016-12)
Feature Pyramid Networks for Object Detection
and 1 more not named here
get_imdb 4 other papers
4 dated earlier
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1506.02025 (2015-06)
Spatial Transformer Networks
1507.00448 (2015-07)
Cross Modal Distillation for Supervision Transfer
and 1 more not named here
im_list_to_blob 2 other papers
1 dated earlier, 1 later
1507.00448 (2015-07)
Cross Modal Distillation for Supervision Transfer
1909.12605 (2019-09)
Towards Real-Time Multi-Object Tracking
get_output_dir 1 other paper
1 dated earlier
1507.00448 (2015-07)
Cross Modal Distillation for Supervision Transfer

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

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that transfer the object detection problem to an image classification problem using Multiple Instance Learning (MIL), our strategy generates proposal clusters to learn refined instance classifiers by an iterative process. The proposals in the same cluster are spatially adjacent and associated with the same object. This prevents the network from concentrating too much on parts of objects instead of whole objects. We first show that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then show that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method. The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one. Experiments are conducted on the PASCAL VOC, ImageNet detection, and MS-COCO benchmarks for WSOD. Results show that our method outperforms the previous state of the art significantly.

For agents

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

get_harvested_code_for_paper("1807.03342")
get_code_for_paper("1807.03342")
have("1807.03342")

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

curl https://syntology.ai/api/ran/1807.03342.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.03342.svg)](https://syntology.ai/paper/1807.03342)

Connect an agent — have() is free.