</> Code with Papers by Syntology

Methods › General › Feedforward Networks › Mix-FFN

Mix-FFN

47 papers tagged archive 2025-07-28

Introduced by Enze Xie et al. in SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Mix-FFN is a feedforward layer used in the SegFormer architecture. ViT uses positional encoding (PE) to introduce the location information. However, the resolution of PE is fixed. Therefore, when the test resolution is different from the training one, the positional code needs to be interpolated and this often leads to dropped accuracy. To alleviate this problem, CPVT uses 3 ×3 Conv together with the PE to implement a data-driven PE. The authors of Mix-FFN argue that positional encoding is actually not necessary for semantic segmentation. Instead, they use Mix-FFN which considers the effect of zero padding to leak location information, by directly using a 3 ×3 Conv in the feed-forward network (FFN). Mix-FFN can be formulated as:

𝐱ₒᵤₜ=MLP(GELU(Conv_(3 ×3)(MLP(𝐱_(i n)))))+𝐱_(i n)

where 𝐱_(i n) is the feature from a self-attention module. Mix-FFN mixes a 3 ×3 convolution and an MLP into each FFN.

PaperSource

Papers archive 2025-07-28

30 shown of 47, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 57 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation33
Segmentation22
Decoder7
Autonomous Driving4
Image Segmentation4
Data Augmentation3
Diversity3
GPU3
Image Classification3
Instance Segmentation3
Object Detection3
object-detection3
2D Semantic Segmentation2
Burned Area Delineation2
CPU2
Change Detection2
Disaster Response2
Land Cover Classification2
Object2
Prediction2

Usage over time archive 2025-07-28

Papers per year tagged with Mix-FFN: 2021 to 2025, peak 14 14 0 2021: 4 papers 2021 2022: 10 papers 2022 2023: 14 papers 2023 2024: 13 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (47 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Feedforward Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections