SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.07559 · 2019

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

arXiv · PDF · Open in the Atlas

Code that ran

4 of 11 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 4 have no contract verdict; 0 failures of our instrument; 7 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/1911.07559.json · badge: /api/ran/1911.07559.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
bitcjm/PaddleVideo community (classifier label)
classifier basis not recorded on the link
4 ran · 7 no recorded run
FunctionStatusWhere it lives
evaluate_scenes Ran
ran on a synthesized input
bitcjm/PaddleVideo/paddlevideo/metrics/transnetv2_metric.py
code served (permissive licence) · get_code("5f86f604143de119")
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

# Construct ground truth scenes: list of [start_frame, end_frame] pairs
# This represents 2 scenes in a video
gt_scenes = np.array([
    [0, 5],
    [6, 9]
], dtype=np.int32)

# Construct predicted scenes: similar structure
# These will be compared against ground truth
pred_scenes = np.array([
    [0, 5],
    [6, 9]
], dtype=np.int32)

# Tolerance parameter for frame miss tolerance
n_frames_miss_tolerance = 2

ARGS = {
    "gt_scenes": gt_scenes,
    "pred_scenes": pred_scenes,
    "n_frames_miss_tolerance": n_frames_miss_tolerance,
}
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 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
expand_bbox Ran
ran on a synthesized input
bitcjm/PaddleVideo/paddlevideo/modeling/bbox_utils.py
code served (permissive licence) · get_code("c434ee22884ca564")
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 a small array of bounding boxes in format [x1, y1, x2, y2]
# Using 2 bboxes as a minimal batch
bboxes = np.array([
    [10.0, 20.0, 50.0, 80.0],
    [100.0, 150.0, 200.0, 250.0]
], dtype=np.float32)

scale = 1.5

ARGS = {
    "bboxes": bboxes,
    "scale": scale
}
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
make_image_key Ran
ran on a synthesized input
bitcjm/PaddleVideo/paddlevideo/metrics/ava_utils.py
code served (permissive licence) · get_code("bdec6fff71733f82")
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 str. 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

ARGS = {
    'video_id': 'video_001',
    'timestamp': 42.5
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
predictions_to_scenes Ran
ran on a synthesized input
bitcjm/PaddleVideo/paddlevideo/metrics/transnetv2_metric.py
code served (permissive licence) · get_code("3da0df168740c1aa")
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 int, shape (3, 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 numpy as np

# The function predictions_to_scenes takes a single parameter: predictions
# It iterates through predictions, treating each element as 0 or 1
# and identifies scenes (contiguous regions) based on transitions
# So predictions should be an array-like of binary values (0s and 1s)

# Create a simple predictions array with some transitions
predictions = np.array([0, 0, 1, 1, 1, 0, 0, 1, 1, 0], dtype=np.int32)

ARGS = {
    "predictions": predictions
}
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 int, shape (3, 2) — shape (3, 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
build_assigner Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/modeling/builder.py
code served (permissive licence) · get_code("53a344650c2ae128")
How it ran

no invocation recorded.

build_backbone Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/modeling/builder.py
code served (permissive licence) · get_code("bd2c60c19da90ad9")
How it ran

no invocation recorded.

build_batch_pipeline Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/loader/builder.py
code served (permissive licence) · get_code("5dfa351278eb7273")
How it ran

no invocation recorded.

build_dataset Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/loader/builder.py
code served (permissive licence) · get_code("c5410bba5ff1d47e")
How it ran

no invocation recorded.

build_pipeline Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/loader/builder.py
code served (permissive licence) · get_code("47873a8759273c0e")
How it ran

no invocation recorded.

build_roi_extractor Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/modeling/builder.py
code served (permissive licence) · get_code("3dc760b0bc6bfea5")
How it ran

no invocation recorded.

create_scene_based_summaries Not yet run
unverified (harvested, no recorded run)
bitcjm/PaddleVideo/paddlevideo/metrics/transnetv2_metric.py
code served (permissive licence) · get_code("1e52fb40ae4513b2")
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, 11 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 7 the same month, 11 later) and 0 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
expand_bbox 4 other papers
1 the same month, 3 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2004.10934 (2020-04)
YOLOv4: Optimal Speed and Accuracy of Object Detection
2106.13230 (2021-06)
Video Swin Transformer
and 1 more not named here
predictions_to_scenes 3 other papers
1 the same month, 2 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2008.04838 (2020-08)
TransNet V2: An effective deep network architecture for fast shot transition detection
2106.13230 (2021-06)
Video Swin Transformer
build_assigner 2 other papers
1 the same month, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2106.13230 (2021-06)
Video Swin Transformer
build_backbone 2 other papers
1 the same month, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2106.13230 (2021-06)
Video Swin Transformer
build_roi_extractor 2 other papers
1 the same month, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2106.13230 (2021-06)
Video Swin Transformer
create_scene_based_summaries 2 other papers
1 the same month, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2106.13230 (2021-06)
Video Swin Transformer
evaluate_scenes 2 other papers
1 the same month, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
2106.13230 (2021-06)
Video Swin Transformer
build_batch_pipeline 1 other paper
1 later
2106.13230 (2021-06)
Video Swin Transformer
build_dataset 1 other paper
1 later
2106.13230 (2021-06)
Video Swin Transformer
build_pipeline 1 other paper
1 later
2106.13230 (2021-06)
Video Swin Transformer
make_image_key 1 other paper
1 later
2106.13230 (2021-06)
Video Swin Transformer

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

In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key components: 1) A novel Feature Attention (FA) module combines Channel Attention with Pixel Attention mechanism, considering that different channel-wise features contain totally different weighted information and haze distribution is uneven on the different image pixels. FA treats different features and pixels unequally, which provides additional flexibility in dealing with different types of information, expanding the representational ability of CNNs. 2) A basic block structure consists of Local Residual Learning and Feature Attention, Local Residual Learning allowing the less important information such as thin haze region or low-frequency to be bypassed through multiple local residual connections, let main network architecture focus on more effective information. 3) An Attention-based different levels Feature Fusion (FFA) structure, the feature weights are adaptively learned from the Feature Attention (FA) module, giving more weight to important features. This structure can also retain the information of shallow layers and pass it into deep layers. The experimental results demonstrate that our proposed FFA-Net surpasses previous state-of-the-art single image dehazing methods by a very large margin both quantitatively and qualitatively, boosting the best published PSNR metric from 30.23db to 36.39db on the SOTS indoor test dataset. Code has been made available at GitHub.

For agents

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

get_harvested_code_for_paper("1911.07559")
get_code_for_paper("1911.07559")
have("1911.07559")

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

curl https://syntology.ai/api/ran/1911.07559.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.07559.svg)](https://syntology.ai/paper/1911.07559)

Connect an agent — have() is free.