Search Results for author:
Found 138 papers, 63 papers with code
SCaLE: Supervised and Cascaded Laplacian Eigenmaps for Visual Object Recognition Based on Nearest Neighbors
In this paper we develop a novel deep learning method that facilitates examplebased visual object category recognition.
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Ranked #174 on
Image Classification
on CIFAR-100
Automatic Photo Adjustment Using Deep Neural Networks
Many photographic styles rely on subtle adjustments that depend on the image content and even its semantics.
Visual Saliency Based on Multiscale Deep Features
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision.
Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification
Recent work on scene classification still makes use of generic CNN features in a rudimentary manner.
HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Deep Contrast Learning for Salient Object Detection
Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream.
Ranked #19 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs).
LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.
Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features.
Visual Saliency Detection Based on Multiscale Deep CNN Features
The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature.
Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data.
Instance-Level Salient Object Segmentation
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks.
Ranked #15 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
Predicting membrane protein contacts from non-membrane proteins by deep transfer learning
Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).
Neural Style Transfer: A Review
We first propose a taxonomy of current algorithms in the field of NST.
DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling
This system has a labor-efficient sketching interface, that allows the user to draw freehand imprecise yet expressive 2D lines representing the contours of facial features.
Folding membrane proteins by deep transfer learning
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network.
Context-Aware Semantic Inpainting
Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context.
Piecewise Flat Embedding for Image Segmentation
We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation.
Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.
Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.
Ranked #15 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Contrast-Oriented Deep Neural Networks for Salient Object Detection
In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations.
Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks
While digital image quality is constantly being improved, taking high-quality photos of digital screens still remains challenging because the photos are often contaminated with moir\'{e} patterns, a result of the interference between the pixel grids of the camera sensor and the device screen.
Ranked #6 on
Image Enhancement
on TIP 2018
ReCoNet: Real-time Coherent Video Style Transfer Network
Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos.
Ranked #4 on
Semantic Segmentation
on FMB Dataset
CaricatureShop: Personalized and Photorealistic Caricature Sketching
To construct the mapping between 2D sketches and a vertex-wise scaling field, a novel deep learning architecture is developed.
Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectification
With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component.
Automatic Image Stylization Using Deep Fully Convolutional Networks
Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent.
Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
Transductive Zero-Shot Learning with Visual Structure Constraint
Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i. e. alleviate the above domain shift problem).
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks.
Ranked #21 on
Fine-Grained Image Classification
on CUB-200-2011
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint.
Ranked #40 on
Semantic Segmentation
on PASCAL Context
Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment
As a concrete example, a database of over 1. 2 million visual objects has been built using the proposed method, and has been successfully used in various data-driven image applications.
Multi-source weak supervision for saliency detection
To this end, we propose a unified framework to train saliency detection models with diverse weak supervision sources.
A Benchmark for Edge-Preserving Image Smoothing
This benchmark includes an image dataset with groundtruth image smoothing results as well as baseline algorithms that can generate competitive edge-preserving smoothing results for a wide range of image contents.
Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks.
ROSA: Robust Salient Object Detection against Adversarial Attacks
To our knowledge, this paper is the first one that mounts successful adversarial attacks on salient object detection models and verifies that adversarial samples are effective on a wide range of existing methods.
Relationship-Embedded Representation Learning for Grounding Referring Expressions
Unfortunately, existing work on grounding referring expressions fails to accurately extract multi-order relationships from the referring expression and associate them with the objects and their related contexts in the image.
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on
Medical Object Detection
on DeepLesion
Motion Guided Attention for Video Salient Object Detection
In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images.
Dynamic Graph Attention for Referring Expression Comprehension
In this paper, we explore the problem of referring expression comprehension from the perspective of language-driven visual reasoning, and propose a dynamic graph attention network to perform multi-step reasoning by modeling both the relationships among the objects in the image and the linguistic structure of the expression.
Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation
Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis.
Self-Enhanced Convolutional Network for Facial Video Hallucination
It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames.
Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
When Relation Networks meet GANs: Relation GANs with Triplet Loss
Though recent research has achieved remarkable progress in generating realistic images with generative adversarial networks (GANs), the lack of training stability is still a lingering concern of most GANs, especially on high-resolution inputs and complex datasets.
Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation
The midline related pathological image features are crucial for evaluating the severity of brain compression caused by stroke or traumatic brain injury (TBI).
Kernel Quantization for Efficient Network Compression
Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio.
Graph-Structured Referring Expression Reasoning in The Wild
The linguistic structure of a referring expression provides a layout of reasoning over the visual contents, and it is often crucial to align and jointly understand the image and the referring expression.
ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities
Instance level detection of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images.
Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation
Nevertheless, there are still great challenges with brain midline delineation, such as the largely deformed midline caused by the mass effect and the possible morphological failure that the predicted midline is not a connected curve.
Online Alternate Generator against Adversarial Attacks
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations.
Rethinking the Extraction and Interaction of Multi-Scale Features for Vessel Segmentation
Analyzing the morphological attributes of blood vessels plays a critical role in the computer-aided diagnosis of many cardiovascular and ophthalmologic diseases.
Contralaterally Enhanced Networks for Thoracic Disease Detection
Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals.
The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision
We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.
Adaptive noise imitation for image denoising
Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.
Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image.
Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
Ranked #4 on
Medical Object Detection
on DeepLesion
Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
Grounding referring expressions in RGBD image has been an emerging field.
Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works.
Ranked #23 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Scene-Intuitive Agent for Remote Embodied Visual Grounding
Intuitively, we comprehend the semantics of the instruction to form an overview of where a bathroom is and what a blue towel is in mind; then, we navigate to the target location by consistently matching the bathroom appearance in mind with the current scene.
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.
Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation
In this paper, we show that such process can be integrated into the one-shot segmentation task which is a very challenging but meaningful topic.
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
Pseudo labeling expands the number of ``labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning.
A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
In this paper, we propose an Anatomy-aware Graph convolutional Network (AGN), which is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability.
Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.
SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation
Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis.
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation
In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.
Bottom-Up Shift and Reasoning for Referring Image Segmentation
In this paper, we tackle the challenge by jointly performing compositional visual reasoning and accurate segmentation in a single stage via the proposed novel Bottom-Up Shift (BUS) and Bidirectional Attentive Refinement (BIAR) modules.
GREN: Graph-Regularized Embedding Network for Weakly-Supervised Disease Localization in X-ray Images
To model the relationship, we propose the Graph Regularized Embedding Network (GREN), which leverages the intra-image and inter-image information to locate diseases on chest X-ray images.
Multi-scale Matching Networks for Semantic Correspondence
We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks.
Ranked #11 on
Semantic correspondence
on SPair-71k
GraphFPN: Graph Feature Pyramid Network for Object Detection
State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using neural networks with a fixed topology.
ConvNets vs. Transformers: Whose Visual Representations are More Transferable?
Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets.
CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation
Data augmentation is a widely used strategy that improves the training of CNNs, and the design of the augmentation method for brain lesion segmentation is still an open problem.
ME-PCN: Point Completion Conditioned on Mask Emptiness
Main-stream methods predict the missing shapes by decoding a global feature learned from the input point cloud, which often leads to deficient results in preserving topology consistency and surface details.
Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage.
nnFormer: Interleaved Transformer for Volumetric Segmentation
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community.
Ranked #1 on
Medical Image Segmentation
on Synapse
Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts
From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations.
Scale-Invariant Teaching for Semi-Supervised Object Detection
Furthermore, the limited annotations in semi-supervised learning scale up the challenges: large variance of object sizes and class imbalance (i. e., the extreme ratio between background and object), hindering the performance of prior arts.
Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition
Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors.
Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation.
Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports
Pre-training lays the foundation for recent successes in radiograph analysis supported by deep learning.
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training
The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.
Ranked #1 on
Medical Object Detection
on DeepLesion
Cross-Modality Deep Feature Learning for Brain Tumor Segmentation
Recent advances in machine learning and prevalence of digital medical images have opened up an opportunity to address the challenging brain tumor segmentation (BTS) task by using deep convolutional neural networks.
Real-time automatic polyp detection in colonoscopy using feature enhancement module and spatiotemporal similarity correlation unit
In order to solve these problems, our method combines the two-dimensional (2-D) CNN-based real-time object detector network with spatiotemporal information.
BOAT: Bilateral Local Attention Vision Transformer
To improve efficiency, recent Vision Transformers adopt local self-attention mechanisms, where self-attention is computed within local windows.
PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated.
Representation Learning
Weakly supervised Semantic Segmentation
+1
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates.
Ranked #1 on
Few-Shot Learning
on Mini-ImageNet - 1-Shot Learning
Scale-Equivalent Distillation for Semi-Supervised Object Detection
Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
Compound Domain Generalization via Meta-Knowledge Encoding
Such holistic semantic structure, referred to as meta-knowledge here, is crucial for learning generalizable representations.
Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis
Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
Domain Invariant Model with Graph Convolutional Network for Mammogram Classification
To resolve this problem, we propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN), which only exploits invariant disease-related features from multiple domains.
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.
Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance
Although deep learning algorithms have been intensively developed for computer-aided tuberculosis diagnosis (CTD), they mainly depend on carefully annotated datasets, leading to much time and resource consumption.
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge.
Ranked #3 on
Image Classification
on Clothing1M
(using extra training data)
One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement
As an important upstream task for many medical applications, supervised landmark localization still requires non-negligible annotation costs to achieve desirable performance.
Neighborhood Collective Estimation for Noisy Label Identification and Correction
Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization.
Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis
On the LIDC-IDRI benchmark dataset for benign-malignant classification of pulmonary nodules in CT images, our method achieves a new state-of-the-art accuracy of 95. 36\% and an AUC of 96. 54\%.
A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective
Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (\emph{e. g.,} social network analysis and recommender systems), computer vision (\emph{e. g.,} object detection and point cloud learning), and natural language processing (\emph{e. g.,} relation extraction and sequence learning), to name a few.
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one.
UNet-2022: Exploring Dynamics in Non-isomorphic Architecture
These phenomena indicate the potential of UNet-2022 to become the model of choice for medical image segmentation.
RankDNN: Learning to Rank for Few-shot Learning
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
Geometry-Aware Network for Domain Adaptive Semantic Segmentation
Moreover, to improve the 2D classifier in the target domain, we perform domain-invariant geometric adaptation from source to target and unify the 2D semantic and 3D geometric segmentation results in two domains.
MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence
Semantic correspondence have built up a new way for object recognition.
PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis
Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views.
I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation
This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation
To tackle the challenges caused by the sparsity and anisotropy of vessels, a higher percentage of graph nodes are distributed in areas that potentially contain vessels while a higher percentage of edges follow the orientation of potential nearbyvessels.
GraVIS: Grouping Augmented Views from Independent Sources for Dermatology Analysis
Self-supervised representation learning has been extremely successful in medical image analysis, as it requires no human annotations to provide transferable representations for downstream tasks.
Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation
Since the two tasks rely on similar feature information, the unlabeled data effectively enhances the representation of the network to the lesion regions and further improves the segmentation performance.
Adaptive Context Selection for Polyp Segmentation
To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM).
Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling
Protein representation learning has primarily benefited from the remarkable development of language models (LMs).
Advancing Radiograph Representation Learning with Masked Record Modeling
Modern studies in radiograph representation learning rely on either self-supervision to encode invariant semantics or associated radiology reports to incorporate medical expertise, while the complementarity between them is barely noticed.
EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Learning image classification and image generation using the same set of network parameters is a challenging problem.
Multi-Level Contrastive Learning for Dense Prediction Task
We extend our pretext task to supervised pre-training, which achieves a similar performance to self-supervised learning.
A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics
During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results.
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
SketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling
User studies demonstrate the superiority of our system over existing modeling tools in terms of the ease to use and visual quality of results.
Improved Distribution Matching for Dataset Condensation
In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising.
EMS: 3D Eyebrow Modeling from Single-view Images
Three modules are then carefully designed: RootFinder firstly localizes the fiber root positions which indicates where to grow; OriPredictor predicts an orientation field in the 3D space to guide the growing of fibers; FiberEnder is designed to determine when to stop the growth of each fiber.
Activate and Reject: Towards Safe Domain Generalization under Category Shift
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur.
B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels.
FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability.
Leveraging Frequency Domain Learning in 3D Vessel Segmentation
In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models, which can reduce computational expenses while preserving global receptive fields within the network.
Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
Once the graph has been refined, Adaptive Betweenness Clustering is introduced to facilitate semantic transfer by using across-domain betweenness clustering and within-domain betweenness clustering, thereby propagating semantic label information from labeled samples across domains to unlabeled target data.
Inter-Domain Mixup for Semi-Supervised Domain Adaptation
However, existing SSDA work fails to make full use of label information from both source and target domains for feature alignment across domains, resulting in label mismatch in the label space during model testing.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models
Parameter-efficient fine-tuning (PEFT) that was initially developed for exploiting pre-trained large language models has recently emerged as an effective approach to perform transfer learning on computer vision tasks.
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining
However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism.
Progressive Conservative Adaptation for Evolving Target Domains
Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism.
SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging
This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework, specifically designed for liver lesion classification in 3D multi-phase CT and MR imaging with varying phase counts.
RegionGPT: Towards Region Understanding Vision Language Model
Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions.
DreamDA: Generative Data Augmentation with Diffusion Models
The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor.
OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation
Recent advances in Iterative Vision-and-Language Navigation (IVLN) introduce a more meaningful and practical paradigm of VLN by maintaining the agent's memory across tours of scenes.
Propagating Over Phrase Relations for One-Stage Visual Grounding
Phrase level visual grounding aims to locate in an image the corresponding visual regions referred to by multiple noun phrases in a given sentence.
