{"ID":2844824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05034","arxiv_id":"2511.05034","title":"Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation","abstract":"Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.Training an end-to-end WSI representation model poses significant challenges, as a standard gigapixel slide can contain tens of thousands of image tiles, making it difficult to compute gradients of all tiles in a single mini-batch due to current GPU limitations. To address this challenge, we propose a method of dynamic residual encoding with slide-level contrastive learning (DRE-SLCL) for end-to-end WSI representation. Our approach utilizes a memory bank to store the features of tiles across all WSIs in the dataset. During training, a mini-batch usually contains multiple WSIs. For each WSI in the batch, a subset of tiles is randomly sampled and their features are computed using a tile encoder. Then, additional tile features from the same WSI are selected from the memory bank. The representation of each individual WSI is generated using a residual encoding technique that incorporates both the sampled features and those retrieved from the memory bank. Finally, the slide-level contrastive loss is computed based on the representations and histopathology reports ofthe WSIs within the mini-batch. Experiments conducted over cancer subtyping, cancer recognition, and mutation prediction tasks proved the effectiveness of the proposed DRE-SLCL method.","short_abstract":"Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.Training an end-to-end WSI representation model poses significant challenges, as a standard gigapixel slide can contain tens of thousands of image tiles, making it difficult to compute gradients of all ti...","url_abs":"https://arxiv.org/abs/2511.05034","url_pdf":"https://arxiv.org/pdf/2511.05034v1","authors":"[\"Jing Jin\",\"Xu Liu\",\"Te Gao\",\"Zhihong Shi\",\"Yixiong Liang\",\"Ruiqing Zheng\",\"Hulin Kuang\",\"Min Zeng\",\"Shichao Kan\"]","published":"2025-11-07T07:17:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}