SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.02713 · 2020

Bifurcated backbone strategy for RGB-D salient object detection

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2007.02713.json · badge: /api/ran/2007.02713.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
zyjwuyan/BBS-Net canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
DengPingFan/BBS-Net community (classifier label)
classifier basis: plan_row
1 ran · 0 no recorded run
FunctionStatusWhere it lives
adjust_lr Ran
ran, honoured the contract we drafted
DengPingFan/BBS-Net/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from CSYSI/DPU-Former, is pointer only (licence: NONE) · get_code("1a4b7ff9d3c48bd7")
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 CSYSI/DPU-Former, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
zyjwuyan/BBS-Net/models/BBSNet_model.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

cv_random_flip Ran
ran, honoured the contract we drafted
zyjwuyan/BBS-Net/data.py
code served (permissive licence) · get_code("c5900dcd35b2d0a3")
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.

from PIL import Image
import random

# Create small test images using PIL
# The function expects PIL Image objects with transpose method
img = Image.new('RGB', (4, 3), color='red')
label = Image.new('L', (4, 3), color=128)
depth = Image.new('L', (4, 3), color=64)

ARGS = {
    'img': img,
    'label': label,
    'depth': depth,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — 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
randomCrop Ran
ran; our contract draft was wrong, not the code
zyjwuyan/BBS-Net/data.py
code served (permissive licence) · get_code("7edae4532113d306")
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.

from PIL import Image
import numpy as np

# Create mock image objects with the required .size attribute and .crop() method
class MockImage:
    def __init__(self, width, height):
        self.size = (width, height)
        self.data = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
    
    def crop(self, box):
        # box is (left, top, right, bottom)
        # Return a new MockImage with cropped dimensions
        left, top, right, bottom = box
        cropped_width = right - left
        cropped_height = bottom - top
        new_image = MockImage(cropped_width, cropped_height)
        return new_image

# Create test images with distinct sizes to probe dimensions
image = MockImage(200, 150)
label = MockImage(200, 150)
depth = MockImage(200, 150)

ARGS = {
    "image": image,
    "label": label,
    "depth": depth
}
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 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
randomRotation Not yet run
unverified (harvested, no recorded run)
zyjwuyan/BBS-Net/data.py
code served (permissive licence) · get_code("2ce2ebcbdb96d573")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 5 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
conv3x3 686 other papers
238 dated earlier, 16 the same month, 431 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
cv_random_flip 3 other papers
3 later
Ji_Calibrated_RGB-D_Salient_Object_Detection_CVPR_2021_paper (2021 (year only))
Calibrated RGB-D Salient Object Detection
2205.07179 (2022-05)
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
2407.06780 (2024-07)
CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection
randomCrop 3 other papers
3 later
Ji_Calibrated_RGB-D_Salient_Object_Detection_CVPR_2021_paper (2021 (year only))
Calibrated RGB-D Salient Object Detection
2205.07179 (2022-05)
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
2407.06780 (2024-07)
CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection
randomRotation 3 other papers
3 later
Ji_Calibrated_RGB-D_Salient_Object_Detection_CVPR_2021_paper (2021 (year only))
Calibrated RGB-D Salient Object Detection
2205.07179 (2022-05)
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
2407.06780 (2024-07)
CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection
adjust_lr 2 other papers
2 later
2203.14291 (2022-03)
Video Polyp Segmentation: A Deep Learning Perspective
2506.21866 (2025-06)
Dual-Perspective United Transformer for Object Segmentation in Optical Remote Sensing Images

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

Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach ($\sim 4 \%$ improvement in S-measure $vs.$ the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.

For agents

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

get_harvested_code_for_paper("2007.02713")
get_code_for_paper("2007.02713")
have("2007.02713")

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

curl https://syntology.ai/api/ran/2007.02713.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.02713.svg)](https://syntology.ai/paper/2007.02713)

Connect an agent — have() is free.