Search Results for author:
Found 33 papers, 10 papers with code
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching
Network quantization is essential for deploying deep models to IoT devices due to the high efficiency, no matter on special hardware like TPU or general hardware like CPU and GPU.
Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce
In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation.
Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation
This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology.
Improving Transferability for Domain Adaptive Detection Transformers
We implement the findings and the alignment modules into our adaptation method, and it benchmarks the DETR-style detector on the domain shift settings.
Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules
We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations for a prediction to help both users and business operators understand why the prediction is made; 3) transferable rules, generating reusable rules to accelerate the deployment of a KG to new systems.
Image Magnification Network for Vessel Segmentation in OCTA Images
Optical coherence tomography angiography (OCTA) is a novel non-invasive imaging modality that allows micron-level resolution to visualize the retinal microvasculature.
DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
In light of this missing, we propose the very first framework that employs neural architecture search to automatic model design for private deep learning, dubbed as DPNAS.
Improving Binary Neural Networks through Fully Utilizing Latent Weights
Binary Neural Networks (BNNs) rely on a real-valued auxiliary variable W to help binary training.
A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease
In parallel, our imaging network projects multimodal data onto a set of latent embeddings.
HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap
In particular, our HIH reaches 4. 08 NME (Normalized Mean Error) on WFLW, and 3. 21 on COFW, which exceeds previous methods by a significant margin.
Ranked #2 on
Face Alignment
on COFW
You Only Look One-level Feature
From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.
Ranked #113 on
Object Detection
on COCO test-dev
Scaling of Magnetic Dissipation and Particle Acceleration in ABC Fields
Using particle-in-cell (PIC) numerical simulations with electron-positron pair plasma, we study how the efficiencies of magnetic dissipation and particle acceleration scale with the initial coherence length $\lambda_0$ in relation to the system size $L$ of the two-dimensional (2D) `Arnold-Beltrami-Childress' (ABC) magnetic field configurations.
High Energy Astrophysical Phenomena Plasma Physics
G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification
We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers.
IPN-V2 and OCTA-500: Methodology and Dataset for Retinal Image Segmentation
In this work, we propose image projection network V2 (IPN-V2), extending IPN by adding a plane perceptron to enhance the perceptron ability in the horizontal direction.
Simulation of Skin Stretching around the Forehead Wrinkles in Rhytidectomy
Finally, the stress distribution and the residual wrinkles of forehead skin were employed to evaluate the surgical effect.
Location-aware Upsampling for Semantic Segmentation
Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks.
Ranked #27 on
Semantic Segmentation
on PASCAL Context
SpatialFlow: Bridging All Tasks for Panoptic Segmentation
Object location is fundamental to panoptic segmentation as it is related to all things and stuff in the image scene.
Ranked #14 on
Panoptic Segmentation
on COCO test-dev
Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples.
Compact Global Descriptor for Neural Networks
Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks.
Ranked #178 on
Object Detection
on COCO test-dev
Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images
In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images.
FoveaNet: Perspective-aware Urban Scene Parsing
Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors.
A Fast Factorization-based Approach to Robust PCA
Our method can be used as a light-weight, scalable tool for RPCA in the absence of the precise value of the true rank.
LogDet Rank Minimization with Application to Subspace Clustering
Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator.
Deep Domain Adaptation for Describing People Based on Fine-Grained Clothing Attributes
We address the problem of describing people based on fine-grained clothing attributes.
Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
To address this problem, we propose a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning.
Towards Unified Human Parsing and Pose Estimation
We study the problem of human body configuration analysis, more specifically, human parsing and human pose estimation.
Network In Network
With enhanced local modeling via the micro network, we are able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers.
Ranked #32 on
Image Classification
on SVHN
Efficient Maximum Appearance Search for Large-Scale Object Detection
In recent years, efficiency of large-scale object detection has arisen as an important topic due to the exponential growth in the size of benchmark object detection datasets.
Subcategory-Aware Object Classification
In this paper, we introduce a subcategory-aware object classification framework to boost category level object classification performance.
