$SEGM segmentation

Latest papers

1. SpanGuard: Decoupling Instruction Localization from Authorization for Lightweight IPI Defense cs.CR · 19 Oct · 1 hit

   …with their surrounding content and can be partitioned into local regions via lightweight unsupervised segmentation. Once the observation is partitioned this way, the remaining authorization check becomes a…

2. HP-GSBS: Accelerating greedy state boundary search with reusable interval statistics cs.CE · 19 Oct · 3 hits

   …and local refinement further reduce repeated work; CPU, PyTorch CUDA and Triton backends share sequential segmentation decisions. Across seven controlled workloads with two realizations each, median same-input…

3. Residual-Guided Adaptive Tucker Rank Allocation for Parameter-Efficient MCI Conversion Prediction cs.LG · 19 Oct · 1 hit

   …conversion from mild cognitive impairment to Alzheimer's disease within 36 months, using hippocampal segmentation pretraining. Across five random seeds, the proposed method achieves a mean area under the…

4. Visual Memory and Textual Alignment for Cross-Modal Few-Shot Segmentation cs.CV · 19 Oct · 3 hits

   Few-shot segmentation (FSS) aims to segment target objects with limited annotated examples. Recent studies have begun…

5. SlimFormer++: Token Mixing Where It Matters for Efficient 3D Medical Image Segmentation cs.CV · 18 Oct · 4 hits

   To determine where computation is needed in volumetric segmentation networks, we analyze block-level redundancy and stage-wise token-mixer contribution. Centered…

6. PCXR-Copilot: Device-aware pediatric chest radiographic analysis with segmentation, suppression, and edema-related cues cs.CV · 18 Oct · 1 hit

   Patients admitted to pediatric ICU and cardiac ICU often require intensive perioperative support and frequent…

7. Reliability-Preserving Compression for Deployable Medical Image Segmentation eess.IV · 18 Oct · 4 hits

   Post-training compression of pretrained medical segmentation models commonly uses quantization, pruning, or distillation to reduce model size and…

8. Design Considerations in Low-Resource Archival OCR: A Case Study in Lakota cs.CL · 18 Oct · 2 hits

   …OCR that arise in previous work and conversations with community members: constrained training budgets, segmentation noise, scan degradation, and orthographic variance. We demonstrate that fine-tuning VLMs for OCR…