GLEAM is the first tri-modal public glaucoma dataset with fundus, OCT, and visual field images, paired with HAMM, a hierarchical attentive masked modeling framework for multimodal classification.
hub
Deep residual learning for image recognition
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
method 1polarities
use method 1representative citing papers
Releases the DAPWH dataset of 3556 wasp images including 1739 COCO-annotated examples to enable AI models for identifying Ichneumonoidea and associated families.
ELSA is a near-SRAM dataflow architecture realizing elastic inference in SNNs via fine-grained spine/token pipelines, bundled AER, and mini-batch Gustavson products, delivering up to 3.4x speedup and 22.1x energy gains over SOTA accelerators on ResNet-50.
A single shared model performs human activity recognition on arbitrary sensor channel configurations by combining independent channel encoding with metadata-conditioned late fusion and joint optimization.
Petro-SAM adapts SAM via a Merge Block for polarized views plus multi-scale fusion and color-entropy priors to jointly achieve grain-edge and lithology segmentation in petrographic images.
ScaleGNN uses communication-free sampling and 4D parallelism to scale mini-batch GNN training to 2048 GPUs, achieving 3.5x speedup over prior state-of-the-art on ogbn-products.
DBLP is a training-phase-aware bounded-loss transport protocol that reduces end-to-end distributed ML training time by 24.4% on average (up to 33.9%) and achieves up to 5.88x communication speedup during microbursts while maintaining comparable test accuracy.
Randomly initialized networks trained solely via peer-to-peer self-distillation learn useful representations that outperform random baselines on downstream tasks.
MapGCLR applies geospatial contrastive learning on multi-traversal overlapping data to enhance BEV representations for vectorized online HD map construction and reports better performance than supervised baselines in a semi-supervised setup.
Hierarchical federated learning for plant-disease classification shows distinct accuracy-versus-energy trade-offs across EfficientNet-B0, ResNet-50, and MobileNetV3-Large paired with FedAvg, FedProx, and FedAvgM.
citing papers explorer
-
GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification
GLEAM is the first tri-modal public glaucoma dataset with fundus, OCT, and visual field images, paired with HAMM, a hierarchical attentive masked modeling framework for multimodal classification.
-
Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH)
Releases the DAPWH dataset of 3556 wasp images including 1739 COCO-annotated examples to enable AI models for identifying Ichneumonoidea and associated families.
-
ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing
ELSA is a near-SRAM dataflow architecture realizing elastic inference in SNNs via fine-grained spine/token pipelines, bundled AER, and mini-batch Gustavson products, delivering up to 3.4x speedup and 22.1x energy gains over SOTA accelerators on ResNet-50.
-
Channel-Free Human Activity Recognition via Inductive-Bias-Aware Fusion Design for Heterogeneous IoT Sensor Environments
A single shared model performs human activity recognition on arbitrary sensor channel configurations by combining independent channel encoding with metadata-conditioned late fusion and joint optimization.
-
From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation
Petro-SAM adapts SAM via a Merge Block for polarized views plus multi-scale fusion and color-entropy priors to jointly achieve grain-edge and lithology segmentation in petrographic images.
-
Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
ScaleGNN uses communication-free sampling and 4D parallelism to scale mini-batch GNN training to 2048 GPUs, achieving 3.5x speedup over prior state-of-the-art on ogbn-products.
-
DBLP: Phase-Aware Bounded-Loss Transport for Burst-Resilient Distributed ML Training
DBLP is a training-phase-aware bounded-loss transport protocol that reduces end-to-end distributed ML training time by 24.4% on average (up to 33.9%) and achieves up to 5.88x communication speedup during microbursts while maintaining comparable test accuracy.
-
Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus
Randomly initialized networks trained solely via peer-to-peer self-distillation learn useful representations that outperform random baselines on downstream tasks.
-
MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction
MapGCLR applies geospatial contrastive learning on multi-traversal overlapping data to enhance BEV representations for vectorized online HD map construction and reports better performance than supervised baselines in a semi-supervised setup.
-
Performance and Energy Trade-Off Analysis of Hierarchical Federated Learning for Plant Disease Classification
Hierarchical federated learning for plant-disease classification shows distinct accuracy-versus-energy trade-offs across EfficientNet-B0, ResNet-50, and MobileNetV3-Large paired with FedAvg, FedProx, and FedAvgM.