Methods › General › Self-Supervised Learning › SSDS

Self-Supervised Deep Supervision

SSDS

10 papers tagged archive 2025-07-28

Introduced by Amrest Chinkamol et al. in OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation

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

The method exploits the finding that high correlation of segmentation performance among each U-Net's decoder layer -- with discriminative layer attached -- tends to have higher segmentation performance in the final segmentation map. By introducing an "Inter-layer Divergence Loss", based on Kulback-Liebler Divergence, to promotes the consistency between each discriminative output from decoder layers by minimizing the divergence.

If we assume that each decoder layer is equivalent to PDE function parameterized by weight parameter θ:

Decoderᵢ(x;θᵢ) ≡PDE(x;θᵢ)

Then our objective is trying to make each discriminative output similar to each other:

PDE(x; θ_d) ∼PDE(x; θᵢ); 0 ≤i < d

Hence the objective is to minimize ∑ᵢ₌₀ᵈ D_(KL)(ŷ || Decoderᵢ).

PaperSource

Papers archive 2025-07-28

10 shown of 10, 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 24 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
GPU4
CPU2
Re-Ranking2
Abstractive Text Summarization1
Automatic Speech Recognition1
Automatic Speech Recognition (ASR)1
Blocking1
Collaborative Filtering1
Deep Learning1
Diagnostic1
Edge-computing1
Image Segmentation1
Information Retrieval1
Large Language Model1
Medical Image Segmentation1
Natural Language Understanding1
Quantization1
Retinal Vessel Segmentation1
Retrieval1
Speech Recognition1

Usage over time archive 2025-07-28

Papers per year tagged with SSDS: 2022 to 2025, peak 7 7 0 2022: 1 paper 2022 2023: 1 paper 2023 2024: 7 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (10 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

Self-Supervised Learning

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