Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
hub
Title resolution pending
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Hybrid T2I generation with teacher-student pseudo-labeling plus VRAIN context-aware I2I rare-class editing improves LVIS instance segmentation AP, especially on rare categories.
A dual-query scene graph generation method unifies detector-based and query-based reasoning in a single decoder, achieving state-of-the-art results on Visual Genome, Open Images v6, and GQA-200.
A multi-view radar segmentation approach with hypergraphs for structural dependencies and UOT for view alignment reports mIoU gains of 1.7-2.3 points on CARRADA and RADIal benchmarks.
Diffusion-generated, distribution-matched synthetic images enable zero-shot quantized object detectors to outperform prior zero-shot methods and even real-data QAT at 4-bit and 3-bit precision.
SWAN is the first adaptive multimodal network that meets variable compute budgets, optimizes layer use by sample complexity, and drops irrelevant features, cutting FLOPs up to 49% in 3D object detection with minimal accuracy loss.
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
GIF fuses geometrical image features and logical graph topology in a conditional diffusion model to generate high-quality IR drop images for chip layouts, outperforming prior ML methods on CircuitNet-N28 with SSIM 0.78, Pearson 0.95, PSNR 21.77, and NMAE 0.026.
A visualization protocol using unsupervised semantic segmentation outputs reveals positional biases, scaling behaviors, and boundary artifacts in self-supervised ViTs and distinguishes them from locality bias.
GeoFuse fuses aligned road maps with satellite imagery via token/channel interactions and dynamic gating plus contrastive learning, lifting Recall@1 by 3.46% on University-1652 and 23.18% on DenseUAV under weather degradation.
Presents an SSM-based hierarchical feature learning method for medical point clouds that reports superior performance on classification, completion, and segmentation using a new dataset MedPointS.
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.
citing papers explorer
-
How to Evaluate and Refine your CAM
Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
-
TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation
Hybrid T2I generation with teacher-student pseudo-labeling plus VRAIN context-aware I2I rare-class editing improves LVIS instance segmentation AP, especially on rare categories.
-
Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability
A dual-query scene graph generation method unifies detector-based and query-based reasoning in a single decoder, achieving state-of-the-art results on Visual Genome, Open Images v6, and GQA-200.
-
Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation
A multi-view radar segmentation approach with hypergraphs for structural dependencies and UOT for view alignment reports mIoU gains of 1.7-2.3 points on CARRADA and RADIal benchmarks.
-
Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models
Diffusion-generated, distribution-matched synthetic images enable zero-shot quantized object detectors to outperform prior zero-shot methods and even real-data QAT at 4-bit and 3-bit precision.
-
SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations
SWAN is the first adaptive multimodal network that meets variable compute budgets, optimizes layer use by sample complexity, and drops irrelevant features, cutting FLOPs up to 49% in 3D object detection with minimal accuracy loss.
-
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
-
GIF: A Conditional Multimodal Generative Framework for IR Drop Imaging in Chip Layouts
GIF fuses geometrical image features and logical graph topology in a conditional diffusion model to generate high-quality IR drop images for chip layouts, outperforming prior ML methods on CircuitNet-N28 with SSIM 0.78, Pearson 0.95, PSNR 21.77, and NMAE 0.026.
-
Unsupervised Semantic Segmentation Facilitates Model Understanding
A visualization protocol using unsupervised semantic segmentation outputs reveals positional biases, scaling behaviors, and boundary artifacts in self-supervised ViTs and distinguishes them from locality bias.
-
Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse
GeoFuse fuses aligned road maps with satellite imagery via token/channel interactions and dynamic gating plus contrastive learning, lifting Recall@1 by 3.46% on University-1652 and 23.18% on DenseUAV under weather degradation.
-
Hierarchical Feature Learning for Medical Point Clouds via State Space Model
Presents an SSM-based hierarchical feature learning method for medical point clouds that reports superior performance on classification, completion, and segmentation using a new dataset MedPointS.
-
Accuracy Improvement of Cell Image Segmentation Using Feedback Former
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
-
T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.