SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.11819 · ICCV · 2021

Mining Contextual Information Beyond Image for Semantic Segmentation

Jian Wang, Jie Shao, Changhu Wang, Qi Chu, Dongdong Yu, Zhenchao Jin, Tao Gong

arXiv · PDF · Open in the Atlas

Code that ran

None of the 2 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (2 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/2108.11819.json · badge: /api/ran/2108.11819.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
charlespikachu/mcibi marked official in Papers with Code
Papers with Code archive
0 ran · 2 no recorded run
FunctionStatusWhere it lives
FeaturesMemory Not yet run
unverified (harvested, no recorded run)
charlespikachu/mcibi/src/segmentors/mcibi/memory.py
code served (permissive licence) · get_code("8b34af409575ebd2")
How it ran

no invocation recorded.

SelfAttentionBlock Not yet run
unverified (harvested, no recorded run)
charlespikachu/mcibi/src/segmentors/mcibi/memory.py
code served (permissive licence) · get_code("0ec55e35f6ccbca8")
How it ran

no invocation recorded.

Also present in other papers' code

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

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

This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report stateof-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff 1 . * This work was performed while Zhenchao Jin worked as an intern at ByteDance.

For agents

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

get_harvested_code_for_paper("2108.11819")
get_code_for_paper("2108.11819")
have("2108.11819")

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

curl https://syntology.ai/api/ran/2108.11819.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.11819.svg)](https://syntology.ai/paper/2108.11819)

Connect an agent — have() is free.