A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 6representative citing papers
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.
DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF post-processing.
Integrating total variation regularization into U-Net and SegNet yields segmentation results with improved spatial regularity and noise robustness on WBC, CamVid, and SUN-RGBD datasets.
A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.
citing papers explorer
-
Differentiable Surrogate for Detector Simulation and Design with Diffusion Models
A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
-
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
-
DETOUR: A Practical Backdoor Attack against Object Detection
DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.
-
Rethinking Atrous Convolution for Semantic Image Segmentation
DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF post-processing.
-
A Regularized Convolutional Neural Network for Semantic Image Segmentation
Integrating total variation regularization into U-Net and SegNet yields segmentation results with improved spatial regularity and noise robustness on WBC, CamVid, and SUN-RGBD datasets.
-
A review on deep learning techniques for 3D sensed data classification
A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.