Methods › General › Self-Supervised Learning › SSDS
Self-Supervised Deep Supervision
SSDS
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).
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.
-
Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage 6 Jun 2025 · 0 repositories · arXiv:2506.06472
-
Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching 17 Oct 2024 · 0 repositories · arXiv:2410.14740
-
FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search 25 Sep 2024 · 0 repositories · arXiv:2409.16576
-
InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference 8 Sep 2024 · 0 repositories · arXiv:2409.04992
-
LearnedKV: Integrating LSM and Learned Index for Superior Performance on Storage 27 Jun 2024 · 0 repositories · arXiv:2406.18892
-
FastPersist: Accelerating Model Checkpointing in Deep Learning 19 Jun 2024 · 0 repositories · arXiv:2406.13768
-
Automatic Speech Recognition (ASR) for the Diagnosis of pronunciation of Speech Sound Disorders in Korean children 13 Mar 2024 · 0 repositories · arXiv:2403.08187
-
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection 6 Mar 2024 · 1 repository · arXiv:2403.04073
-
ESPN: Memory-Efficient Multi-Vector Information Retrieval 9 Dec 2023 · 1 repository · arXiv:2312.05417
-
OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation 25 Jul 2022 · 1 repository · arXiv:2207.12238
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.
Usage over time archive 2025-07-28
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
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