{"url":"/method/ssds","slug":"ssds","name":"SSDS","full_name":"Self-Supervised Deep Supervision","full_name_withheld":false,"description_markdown":"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.\r\n\r\nIf we assume that each decoder layer is equivalent to PDE function parameterized by weight parameter $\\theta$:\r\n\r\n$Decoder_i(x;\\theta_i) \\equiv PDE(x;\\theta_i)$\r\n\r\nThen our objective is trying to make each discriminative output similar to each other:\r\n\r\n$PDE(x; \\theta_d) \\sim PDE(x; \\theta_i);\\text{ } 0 \\leq i < d$\r\n\r\nHence the objective is to $\\text{minimize} \\sum_{i=0}^{d} D_{KL}(\\hat{y} || Decoder_i)$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation","paper":"/paper/octave-2d-en-face-optical-coherence","first_author":"Amrest Chinkamol","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/octave-2d-en-face-optical-coherence"},"source":{"url":"https://arxiv.org/abs/2207.12238v1","title":"OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Self-Supervised Learning","url":"/methods/category/self-supervised-learning","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":10,"papers_newest_first":[{"paper":null,"title":"Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage","date":"2025-06-06","arxiv_id":"2506.06472","n_code_links":0,"syntology":null},{"paper":null,"title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","date":"2024-10-17","arxiv_id":"2410.14740","n_code_links":0,"syntology":null},{"paper":null,"title":"FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search","date":"2024-09-25","arxiv_id":"2409.16576","n_code_links":0,"syntology":null},{"paper":null,"title":"InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference","date":"2024-09-08","arxiv_id":"2409.04992","n_code_links":0,"syntology":null},{"paper":null,"title":"LearnedKV: Integrating LSM and Learned Index for Superior Performance on Storage","date":"2024-06-27","arxiv_id":"2406.18892","n_code_links":0,"syntology":null},{"paper":null,"title":"FastPersist: Accelerating Model Checkpointing in Deep Learning","date":"2024-06-19","arxiv_id":"2406.13768","n_code_links":0,"syntology":null},{"paper":null,"title":"Automatic Speech Recognition (ASR) for the Diagnosis of pronunciation of Speech Sound Disorders in Korean children","date":"2024-03-13","arxiv_id":"2403.08187","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-dialogue-abstractive","title":"Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection","date":"2024-03-06","arxiv_id":"2403.04073","n_code_links":1,"syntology":null},{"paper":"/paper/espn-memory-efficient-multi-vector","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","date":"2023-12-09","arxiv_id":"2312.05417","n_code_links":1,"syntology":null},{"paper":"/paper/octave-2d-en-face-optical-coherence","title":"OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation","date":"2022-07-25","arxiv_id":"2207.12238","n_code_links":1,"syntology":null}],"papers_shown":10,"tasks":[{"task":null,"name":"GPU","papers":4},{"task":null,"name":"CPU","papers":2},{"task":"/task/re-ranking","name":"Re-Ranking","papers":2},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":1},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/blocking","name":"Blocking","papers":1},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/edge-computing","name":"Edge-computing","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/retinal-vessel-segmentation","name":"Retinal Vessel Segmentation","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":1}],"tasks_shown":20,"n_tasks":24,"usage_by_year":[{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":7},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ssds"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}