Search Results for author:
Found 58 papers, 30 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.
Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images
We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images).
FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs
To this end, we devised the FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image annotations consisting of the category and position of objects, region descriptions, text information, as well as image dense captions.
Automated Quantification of Hyperreflective Foci in SD-OCT With Diabetic Retinopathy
However, lack of efficient quantitative tools for evaluating the HFs has deprived ophthalmologist of assessing the volume of HFs.
OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer
Open-vocabulary object detection focusing on detecting novel categories guided by natural language.
Test-Time Generative Augmentation for Medical Image Segmentation
In this paper, we propose a novel approach to enhance medical image segmentation during test time.
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection.
Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models
In tandem with autoencoders, we propose cascaded diffusion processes to synthesize high-resolution OCT volumes with a global-to-local refinement process, amortizing the memory and computational demands.
Adaptive Fuzzy C-Means with Graph Embedding
Fuzzy clustering algorithms can be roughly categorized into two main groups: Fuzzy C-Means (FCM) based methods and mixture model based methods.
VRP-SAM: SAM with Visual Reference Prompt
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model.
Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
Measurements of spherical equivalent and axial length are the gold standards for identifying high myopia, but the available image data for matching them is scarce.
Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation
Moreover, to address the semantic conflicts between image and frequency domains, the forgery-aware mutual module is developed to further enable the effective interaction of disparate image and frequency features, resulting in aligned and comprehensive visual forgery representations.
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.
Learn Single-horizon Disease Evolution for Predictive Generation of Post-therapeutic Neovascular Age-related Macular Degeneration
We propose a single-horizon disease evolution network (SHENet) to predictively generate post-therapeutic SD-OCT images by inputting pre-therapeutic SD-OCT images with neovascular age-related macular degeneration (nAMD).
Enhancing Your Trained DETRs with Box Refinement
We hope our work will bring the attention of the detection community to the localization bottleneck of current DETR-like models and highlight the potential of the RefineBox framework.
Exploring Effective Factors for Improving Visual In-Context Learning
By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks.
s-Adaptive Decoupled Prototype for Few-Shot Object Detection
To provide precise information for the query image, the prototype is decoupled into task-specific ones, which provide tailored guidance for 'where to look' and 'what to look for', respectively.
DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection
In this paper, we revisit these two assignment methods and find that bringing one-to-many assignment back to end-to-end fully convolutional detectors helps with model convergence.
CAE v2: Context Autoencoder with CLIP Target
That is to say, the smaller the model, the lower the mask ratio needs to be.
Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO.
Ranked #8 on
Object Detection
on COCO test-dev
(using extra training data)
SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks.
Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
We release all the open resources (OpenBG benchmarks) derived from it for the community and report experimental results of KG-centric tasks.
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing.
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}.
Ranked #10 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
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.
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
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 #4 on
Face Alignment
on WFW (Extra Data)
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 #142 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.
OCTA-500: A Retinal Dataset for Optical Coherence Tomography Angiography Study
Optical coherence tomography angiography (OCTA) is a novel imaging modality that has been widely utilized in ophthalmology and neuroscience studies to observe retinal vessels and microvascular systems.
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 #35 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 #17 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 #210 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 #4 on
Face Identification
on DroneSURF
Subcategory-Aware Object Classification
In this paper, we introduce a subcategory-aware object classification framework to boost category level object classification performance.
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.
