VitaminP uses paired H&E-mIF data to train a model that transfers molecular boundary information, enabling accurate whole-cell segmentation directly from routine H&E histology across 34 cancer types.
hub
FedAffect: Few-shot federated learning for facial expression recognition
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
A new large-scale synthetic multi-task benchmark dataset supplying pixel-perfect depth, domain-shifted night imagery, and multi-scale low-resolution pairs for aerial remote sensing.
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
Introduces SCAE with skip connections and LGE to fix detail loss in LDMs for RGB-to-SWIR translation, yielding up to 2x mAP gains and 3.4x on small objects while reaching SOTA FID.
A phase-aware wavelet scattering encoder-decoder improves denoising PSNR by preserving phase in skip connections, with reported gains of +2.17 dB from breaking translation invariance and +1.03 dB from phase preservation.
IAC-LTH accelerates IAC search for medical segmentation by progressively pruning unstable operations via Jensen-Shannon divergence on per-edge importance distributions, delivering comparable patient-level Dice scores with substantially lower wall-clock cost.
MoViD disentangles motion and view features via a view estimator and orthogonal projection with contrastive alignment to deliver viewpoint-invariant 3D pose estimation that cuts errors over 24% with 60% less data and runs at 15 FPS on edge hardware.
A multiscale optimization method using explicit protein backbone geometry reconstructs atomic models from cryo-EM data, showing improved RMSD and TM scores on three simulated datasets.
Empirical evaluation shows age estimation models perform orders of magnitude below identification thresholds on face verification benchmarks, indicating they do not extract identity-discriminative representations.
CellPrior-Net integrates hematoxylin channel prior into a lightweight CNN for nuclei detection and classification in H&E WSIs, claiming comparable accuracy to SOTA with significantly reduced inference time across 10.4M nuclei from diverse datasets.
FedKLPR introduces KL-divergence-guided training, pruning-aware weighted aggregation, and cross-round recovery to achieve 40-42% communication reduction on ResNet-50 while preserving competitive accuracy in federated person re-identification across eight datasets.
citing papers explorer
-
VitaminP: cross-modal learning enables whole-cell segmentation from routine histology
VitaminP uses paired H&E-mIF data to train a model that transfers molecular boundary information, enabling accurate whole-cell segmentation directly from routine H&E histology across 34 cancer types.
-
SyMTRS: Benchmark Multi-Task Synthetic Dataset for Depth, Domain Adaptation and Super-Resolution in Aerial Imagery
A new large-scale synthetic multi-task benchmark dataset supplying pixel-perfect depth, domain-shifted night imagery, and multi-scale low-resolution pairs for aerial remote sensing.
-
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
-
FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
-
Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation
Introduces SCAE with skip connections and LGE to fix detail loss in LDMs for RGB-to-SWIR translation, yielding up to 2x mAP gains and 3.4x on small objects while reaching SOTA FID.
-
Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions
A phase-aware wavelet scattering encoder-decoder improves denoising PSNR by preserving phase in skip connections, with reported gains of +2.17 dB from breaking translation invariance and +1.03 dB from phase preservation.
-
Efficient Search of Implantable Adaptive Cells for Medical Image Segmentation
IAC-LTH accelerates IAC search for medical segmentation by progressively pruning unstable operations via Jensen-Shannon divergence on per-edge importance distributions, delivering comparable patient-level Dice scores with substantially lower wall-clock cost.
-
MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement
MoViD disentangles motion and view features via a view estimator and orthogonal projection with contrastive alignment to deliver viewpoint-invariant 3D pose estimation that cuts errors over 24% with 60% less data and runs at 15 FPS on edge hardware.
-
FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification
FedKLPR introduces KL-divergence-guided training, pruning-aware weighted aggregation, and cross-round recovery to achieve 40-42% communication reduction on ResNet-50 while preserving competitive accuracy in federated person re-identification across eight datasets.
- A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline