Search Results for author:
Found 213 papers, 105 papers with code
AdvMIM: Adversarial Masked Image Modeling for Semi-Supervised Medical Image Segmentation
To this end, we propose to construct an auxiliary masked domain from original domain with masked image modeling and train the transformer to predict the entire segmentation mask with masked inputs to increase supervision signal.
Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey
Popular benchmarks for VLM generalization are further introduced with thorough performance comparisons among the reviewed methods.
Long Coalition Leads to Shrink? The Roles of Tipping and Technology-Sharing in Climate Clubs
This framework highlights the critical role of technology-sharing in fostering long-term climate cooperation under climate tipping uncertainties.
PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony.
Time-Lapse Video-Based Embryo Grading via Complementary Spatial-Temporal Pattern Mining
To bridge this gap, we propose a new task called Video-Based Embryo Grading - the first paradigm that directly utilizes full-length time-lapse monitoring (TLM) videos to predict embryologists' overall quality assessments.
PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents
Photo retouching is integral to photographic art, extending far beyond simple technical fixes to heighten emotional expression and narrative depth.
MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
In this work, we first demonstrate that, under medium batch sizes, MoE surprisingly benefits more from SD than dense models.
Faster and Better LLMs via Latency-Aware Test-Time Scaling
By integrating these two approaches and allocating computational resources properly to each, our latency-optimal TTS enables a 32B model to reach 82. 3% accuracy on MATH-500 within 1 minute and a smaller 3B model to achieve 72. 4% within 10 seconds.
Semantic-enhanced Co-attention Prompt Learning for Non-overlapping Cross-Domain Recommendation
Given the above challenges, we introduce the prompt learning technique for Many-to-one Non-overlapping Cross-domain Sequential Recommendation (MNCSR) and propose a Text-enhanced Co-attention Prompt Learning Paradigm (TCPLP).
Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective
In this paper, we advocate the learnable random walk (LRW) perspective as the instantiation of invariant knowledge, and propose LRW-OOD to realize graph OOD generalization learning.
Novel Extraction of Discriminative Fine-Grained Feature to Improve Retinal Vessel Segmentation
AttUKAN achieves F1 scores of 82. 50%, 81. 14%, 81. 34%, 80. 21% and 80. 09%, along with MIoU scores of 70. 24%, 68. 64%, 68. 59%, 67. 21% and 66. 94% in the above datasets, which are the highest compared to 11 networks for retinal vessel segmentation.
RSFR: A Coarse-to-Fine Reconstruction Framework for Diffusion Tensor Cardiac MRI with Semantic-Aware Refinement
Cardiac diffusion tensor imaging (DTI) offers unique insights into cardiomyocyte arrangements, bridging the gap between microscopic and macroscopic cardiac function.
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
Compared to existing methods, Turbo2K is up to 20$\times$ faster for inference, making high-resolution video generation more scalable and practical for real-world applications.
SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training
Finally, experiments on 8 medical image datasets indicate our SuperCL outperforms existing 12 methods.
An Empirical Study of GPT-4o Image Generation Capabilities
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks.
Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning
Reinforcement learning (RL) holds significant promise for adaptive traffic signal control.
Federated Semantic Learning for Privacy-preserving Cross-domain Recommendation
In the evolving landscape of recommender systems, the challenge of effectively conducting privacy-preserving Cross-Domain Recommendation (CDR), especially under strict non-overlapping constraints, has emerged as a key focus.
POSTA: A Go-to Framework for Customized Artistic Poster Generation
To train our models, we develop the PosterArt dataset, comprising high-quality artistic posters annotated with layout, typography, and pixel-level stylized text segmentation.
Exploiting Inherent Class Label: Towards Robust Scribble Supervised Semantic Segmentation
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process.
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians.
Federated Mixture-of-Expert for Non-Overlapped Cross-Domain Sequential Recommendation
In the real world, users always have multiple interests while surfing different services to enrich their daily lives, e. g., watching hot short videos/live streamings.
Revisiting Medical Image Retrieval via Knowledge Consolidation
In this work, we propose a novel method to consolidate knowledge of hierarchical features and optimisation functions.
MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
We present MagicInfinite, a novel diffusion Transformer (DiT) framework that overcomes traditional portrait animation limitations, delivering high-fidelity results across diverse character types-realistic humans, full-body figures, and stylized anime characters.
Partially Supervised Unpaired Multi-Modal Learning for Label-Efficient Medical Image Segmentation
Specifically, our framework consists of a compact segmentation network with modality specific normalization layers for learning with partially labeled unpaired multi-modal data.
Scalable Reinforcement Learning for Virtual Machine Scheduling
This paper introduces a scalable RL framework, called Cluster Value Decomposition Reinforcement Learning (CVD-RL), to surmount the scalability hurdles inherent in large-scale VMS.
TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction
3D facial reconstruction from a single in-the-wild image is a crucial task in human-centered computer vision tasks.
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
Pre-training vision-language representations on human action videos has emerged as a promising approach to reduce reliance on large-scale expert demonstrations for training embodied agents.
Learning Semantic Facial Descriptors for Accurate Face Animation
Our approach successfully addresses the issue of model-based methods' limitations in high-fidelity identity and the challenges faced by model-free methods in accurate motion transfer.
Toward Model-centric Heterogeneous Federated Graph Learning: A Knowledge-driven Approach
Federated graph learning (FGL) has emerged as a promising paradigm for collaborative machine learning, enabling multiple parties to jointly train models while preserving the privacy of raw graph data.
V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer
Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification.
SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization
Snowfall presents significant challenges for visual data processing, necessitating specialized desnowing algorithms.
Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine
To effectively exploit this unlabeled dataset, we propose the first semi-supervised framework (namely an iterative data engine) consisting of four steps: (1) mirror detection model training, (2) pseudo label prediction, (3) dual guidance scoring, and (4) selection of highly reliable pseudo labels.
DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation
The adaptation process has two stages: the first aligns the models on stable features using a mutual information consistency loss, and the second dynamically adjusts the perturbation level based on the loss from the first stage, encouraging the model to explore a broader range of the target domain while preserving existing performance.
Revisiting the Integration of Convolution and Attention for Vision Backbone
Specifically, in each layer, we use two different ways to represent an image: a fine-grained regular grid and a coarse-grained set of semantic slots.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Federated Domain Generalization via Prompt Learning and Aggregation
Specifically, we propose a novel FedDG framework through Prompt Learning and AggregatioN (PLAN), which comprises two training stages to collaboratively generate local prompts and global prompts at each federated round.
UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture.
Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey
This survey serves as a roadmap for researchers, offering practical guidance for future exploration in the field of INRs.
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
We contend that the key to addressing these challenges lies in accurately decoding both high-level semantics and low-level perception flows, as perceived by the brain in response to video stimuli.
Deep Class-guided Hashing for Multi-label Cross-modal Retrieval
Deep hashing, due to its low cost and efficient retrieval advantages, is widely valued in cross-modal retrieval.
Non-Invasive to Invasive: Enhancing FFA Synthesis from CFP with a Benchmark Dataset and a Novel Network
Fundus imaging is a pivotal tool in ophthalmology, and different imaging modalities are characterized by their specific advantages.
A New Perspective to Boost Performance Fairness for Medical Federated Learning
However, existing fair FL methods ignore the specific characteristics of medical FL applications, i. e., domain shift among the datasets from different hospitals.
Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization
Specifically, we construct a real-world dataset with 85 snowy videos, and then present a Semi-supervised Video Desnowing Network (SemiVDN) equipped by a novel Distribution-driven Contrastive Regularization.
Ranked #2 on
Snow Removal
on RVSD
(using extra training data)
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.
BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
In this paper, we introduce a novel bilateral backdoor to fill in the missing pieces of the puzzle in the cross-modal backdoor and propose a generalized invisible backdoor framework against cross-modal learning (BadCM).
Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint
Recent advancements in adverse weather restoration have shown potential, yet the unpredictable and varied combinations of weather degradations in the real world pose significant challenges.
Cross-conditioned Diffusion Model for Medical Image to Image Translation
First, we propose a Modality-specific Representation Model (MRM) to model the distribution of target modalities.
Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal Reasoning
We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation.
Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model
Based on the above observations, we first devise a Serpentine Interwoven Adaptive (SIA) scan mechanism, which scans UWF-SLO images along curved vessel structures in a snake-like crawling manner.
SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing
Ultimately, we inject the previously generated talking segmentation and style codes into a mask-guided StyleGAN to synthesize video frame.
Timeline and Boundary Guided Diffusion Network for Video Shadow Detection
Moreover, we are the first to introduce the Diffusion model for VSD in which we explore a Space-Time Encoded Embedding (STEE) to inject the temporal guidance for Diffusion to conduct shadow detection.
Language-Driven Interactive Shadow Detection
Based on this dataset, we propose a Referring Shadow-Track Memory Network (RSM-Net) for addressing the RVSD task.
Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation
Audio-driven talking head generation is a significant and challenging task applicable to various fields such as virtual avatars, film production, and online conferences.
RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining
Recently, the linear-complexity operator of the state space models (SSMs) has contrarily facilitated efficient long-term temporal modeling, which is crucial for rain streaks and raindrops removal in videos.
Ranked #1 on
Video deraining
on Video Waterdrop Removal Dataset
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration.
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications.
LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos
To this end, we collect and annotate the first ultrasound video dataset with 100 videos for uterine fibroid segmentation (UFUV).
Ranked #1 on
Video Polyp Segmentation
on SUN-SEG-Easy
UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands.
Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation
However, the incorrect pseudo-labels may corrupt the learned feature and lead to a new problem that the better the model is trained on the old task, the poorer the model performs on the new tasks.
Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset
In response, this study introduces a pioneering framework that leverages a patch-based active domain adaptation approach.
ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection
However, the existing salient object detection (SOD) works only focus on either static RGB-D images or RGB videos, ignoring the collaborating of RGB-D and video information.
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models.
Ranked #12 on
Image Reconstruction
on ImageNet
Decision Boundary-aware Knowledge Consolidation Generates Better Instance-Incremental Learner
Two issues have to be tackled in the new IIL setting: 1) the notorious catastrophic forgetting because of no access to old data, and 2) broadening the existing decision boundary to new observations because of concept drift.
SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications
The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs).
MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks.
DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion.
Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation
Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items.
Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanisms
This paper introduces a novel variant of GFNs, the Dynamic Backtracking GFN (DB-GFN), which improves the adaptability of decision-making steps through a reward-based dynamic backtracking mechanism.
Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields
Our method has two stages: the geometry of the target object and the pre-filtered environmental radiance fields are reconstructed in the first stage, and materials of the target object are estimated in the second stage with the proposed NeP and material-aware cone sampling strategy.
Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration
This is because 3DGS treats each pixel as an isolated, single point rather than as an area, causing insensitivity to changes in the footprints of pixels.
Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal
Although ViWS-Net is proposed to remove adverse weather conditions in videos with a single set of pre-trained weights, it is seriously blinded by seen weather at train-time and degenerates when coming to unseen weather during test-time.
Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model.
Agile Multi-Source-Free Domain Adaptation
Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models.
Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facilitating fine-tuning of SR models without requiring paired high-resolution (HR) images.
Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation
Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way.
Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
In this study, we propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision.
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023.
RelayAttention for Efficient Large Language Model Serving with Long System Prompts
To eliminate such a redundancy, we propose RelayAttention, an attention algorithm that allows reading these hidden states from DRAM exactly once for a batch of input tokens.
Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies
Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans.
An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion
A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients.
Vivim: a Video Vision Mamba for Medical Video Segmentation
To this end, this paper presents a Video Vision Mamba-based framework, dubbed as Vivim, for medical video segmentation tasks.
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation
Our SegMamba, in contrast to Transformer-based methods, excels in whole volume feature modeling from a state space model standpoint, maintaining superior processing speed, even with volume features at a resolution of {$64\times 64\times 64$}.
MCRPL: A Pretrain, Prompt & Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation
To overcome the above challenges, we focus on NMCR, and devise MCRPL as our solution.
A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem.
EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector
Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks.
Learning Diffusion Texture Priors for Image Restoration
When adopting diffusion models for image restoration the crucial challenge lies in how to preserve high-level image fidelity in the randomness diffusion process and generate accurate background structures and realistic texture details.
Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis
Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images.
Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge
The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients.
SegRap2023: A Benchmark of Organs-at-Risk and Gross Tumor Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma
The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis.
Lite-Mind: Towards Efficient and Robust Brain Representation Network
The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval.
GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction
To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.
SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese
To systematically assess the safety of Chinese LLMs, we introduce SuperCLUE-Safety (SC-Safety) - a multi-round adversarial benchmark with 4912 open-ended questions covering more than 20 safety sub-dimensions.
Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos.
Ranked #3 on
Video Polyp Segmentation
on SUN-SEG-Easy
Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation
In this work, we propose the first framework for restoring videos from all adverse weather conditions by developing a video adverse-weather-component suppression network (ViWS-Net).
Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training
Moreover, we develop a multi-level contrastive learning strategy that integrates correspondences across feature-level, image-level, and pixel-level representations to ensure the encoder and decoder capture comprehensive details from representations of varying scales and granularities during the pre-training phase.
Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
In this work, we observe that the distribution gap between the confidence values of correct and incorrect pseudo labels emerges at the very beginning of the training, which can be utilized to filter pseudo labels.
Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data
This paper aims to remove specular highlights from a single object-level image.
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding.
Ranked #1 on
Zero-shot 3D Point Cloud Classification
on ScanNetV2
3D Open-Vocabulary Instance Segmentation
3D Open-Vocabulary Object Detection
+6
Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions
With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities.
Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image.
Federated Pseudo Modality Generation for Incomplete Multi-Modal MRI Reconstruction
In this paper, we propose a novel communication-efficient federated learning framework, namely Fed-PMG, to address the missing modality challenge in federated multi-modal MRI reconstruction.
Rethinking Client Drift in Federated Learning: A Logit Perspective
Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype.
Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery
Our method is verified on these datasets, and experimental results exhibit that the VIS-Net can significantly outperform existing state-of-the-art referring segmentation methods.
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
Existing methods adopt an online-trained classification branch to provide pseudo annotations for supervising the segmentation branch.
SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark
We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE.
A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
In this paper, we focus on the feature distribution skewed FL scenario, a common non-IID situation in real-world applications where data from different clients exhibit varying underlying distributions.
Cross-Modal Vertical Federated Learning for MRI Reconstruction
To this end, we formulate this practical-yet-challenging cross-modal vertical federated learning task, in which shape data from multiple hospitals have different modalities with a small amount of multi-modality data collected from the same individuals.
Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation
For robot-assisted surgery, an accurate surgical report reflects clinical operations during surgery and helps document entry tasks, post-operative analysis and follow-up treatment.
Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset
To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations.
Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification
Moreover, human semantic information and pedestrian identity information are not fully explored.
Automated Prompting for Non-overlapping Cross-domain Sequential Recommendation
Cross-domain Recommendation (CR) has been extensively studied in recent years to alleviate the data sparsity issue in recommender systems by utilizing different domain information.
Multi-Behavior Recommendation with Cascading Graph Convolution Networks
Most existing multi-behavior models fail to capture such dependencies in a behavior chain for embedding learning.
Masked Image Training for Generalizable Deep Image Denoising
To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.
Neural Preset for Color Style Transfer
In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed.
Distribution Aligned Diffusion and Prototype-guided network for Unsupervised Domain Adaptive Segmentation
In order to explore its potential further, we have taken a step forward and considered a more complex scenario in the medical image domain, specifically, under an unsupervised adaptation condition.
DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification
However, while a substantial amount of diffusion-based research has focused on generative tasks, few studies have applied diffusion models to general medical image classification.
HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique.
Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation
Our experimental results also indicate the universality and effectiveness of the proposed model.
Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
Video dehazing aims to recover haze-free frames with high visibility and contrast.
Learning Physical-Spatio-Temporal Features for Video Shadow Removal
Then, we develop a progressive aggregation module to enhance the spatio and temporal characteristics of features maps, and effectively integrate the three kinds of features.
BiFormer: Vision Transformer with Bi-Level Routing Attention
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency.
Ranked #9 on
Object Detection
on COCO 2017
(mAP metric)
GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue
For feature aggregation, it improves feature modeling by allowing the network to learn from both local points and neighboring geometry partitions, resulting in an enlarged data-tailored receptive field.
A Comprehensive Survey on Source-free Domain Adaptation
Over the past decade, domain adaptation has become a widely studied branch of transfer learning that aims to improve performance on target domains by leveraging knowledge from the source domain.
One-Pot Multi-Frame Denoising
Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training.
Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections
We propose a decentralized multi-agent reinforcement learning approach for the control and coordination of mixed traffic by RVs at real-world, complex intersections -- an open challenge to date.
Snow Removal in Video: A New Dataset and A Novel Method
We also develop a deep learning framework for video snow removal.
Ranked #4 on
Snow Removal
on RVSD
ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests
With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially for practical heterogeneous request sequences.
Who is Gambling? Finding Cryptocurrency Gamblers Using Multi-modal Retrieval Methods
Meanwhile, decentralized applications have also attracted intense attention from the online gambling community, with more and more decentralized gambling platforms created through the help of smart contracts.
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method.
Dual Multi-scale Mean Teacher Network for Semi-supervised Infection Segmentation in Chest CT Volume for COVID-19
Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19.
CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion
As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection.
Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive Learning
Preoperative and noninvasive prediction of the meningioma grade is important in clinical practice, as it directly influences the clinical decision making.
NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation
Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information.
Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization
Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL).
Harmonizer: Learning to Perform White-Box Image and Video Harmonization
Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization.
Ranked #7 on
Image Harmonization
on iHarmony4
A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos
Moreover, we learn video-level features to classify the breast lesions of the original video as benign or malignant lesions to further enhance the final breast lesion detection performance in ultrasound videos.
Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation
Shared-account Cross-domain Sequential Recommendation (SCSR) task aims to recommend the next item via leveraging the mixed user behaviors in multiple domains.
Copy Motion From One to Another: Fake Motion Video Generation
3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands.
RSCFed: Random Sampling Consensus Federated Semi-supervised Learning
In this paper, we present a Random Sampling Consensus Federated learning, namely RSCFed, by considering the uneven reliability among models from fully-labeled clients, fully-unlabeled clients or partially labeled clients.
Multi-modal learning for predicting the genotype of glioma
In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks.
BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status.
Weakly Supervised Object Localization as Domain Adaption
To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
Content-Noise Complementary Learning for Medical Image Denoising
In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily.
Motion Prediction via Joint Dependency Modeling in Phase Space
In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics.
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.
Distinguishing Unseen From Seen for Generalized Zero-Shot Learning
In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories.
Background-aware Classification Activation Map for Weakly Supervised Object Localization
In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively.
VMAgent: Scheduling Simulator for Reinforcement Learning
A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling.
Network-wide Multi-step Traffic Volume Prediction using Graph Convolutional Gated Recurrent Neural Network
For instance, our model reduces MAE by 25. 3%, RMSE by 29. 2%, and MAPE by 20. 2%, compared to the state-of-the-art Diffusion Convolutional Recurrent Neural Network (DCRNN) model using the hourly dataset.
Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e. g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest.
Ranked #15 on
Camouflaged Object Segmentation
on PCOD_1200
Domain Adaptive Semantic Segmentation without Source Data
To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore.
Boundary-aware Transformers for Skin Lesion Segmentation
Skin lesion segmentation from dermoscopy images is of great importance for improving the quantitative analysis of skin cancer.
Ranked #5 on
Lesion Segmentation
on ISIC 2018
HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation
Particularly, for the Extrinsic Consistency, we leverage the knowledge across multiple source domains to enforce data-level consistency.
Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal
In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models.
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
Lane detection plays a key role in autonomous driving.
MT-ORL: Multi-Task Occlusion Relationship Learning
Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image.
From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #8 on
Image Dehazing
on Haze4k
Unifying Nonlocal Blocks for Neural Networks
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
Adversarial Energy Disaggregation for Non-intrusive Load Monitoring
Energy disaggregation, also known as non-intrusive load monitoring (NILM), challenges the problem of separating the whole-home electricity usage into appliance-specific individual consumptions, which is a typical application of data analysis.
Bayesian Statistics Guided Label Refurbishment Mechanism: Mitigating Label Noise in Medical Image Classification
BLRM utilizes maximum a posteriori probability (MAP) in the Bayesian statistics and the exponentially time-weighted technique to selectively correct the labels of noisy images.
A Multi-Task Network for Joint Specular Highlight Detection and Removal
Specular highlight detection and removal are fundamental and challenging tasks.
Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion
In this paper, we explore combining deep learning with expert patterns in an explainable fashion.
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
Previous bi-classifier adversarial learning methods only focus on the similarity between the outputs of two distinct classifiers.
UGRec: Modeling Directed and Undirected Relations for Recommendation
In particular, for a directed relation, we transform the head and tail entities into the corresponding relation space to model their relation; and for an undirected co-occurrence relation, we project head and tail entities into a unique hyperplane in the entity space to minimize their distance.
DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendation
Shared-account Cross-domain Sequential recommendation (SCSR) is the task of recommending the next item based on a sequence of recorded user behaviors, where multiple users share a single account, and their behaviours are available in multiple domains.
Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement.
Learning the Superpixel in a Non-iterative and Lifelong Manner
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence.
Triple-cooperative Video Shadow Detection
The bottleneck is the lack of a well-established dataset with high-quality annotations for video shadow detection.
Involution: Inverting the Inherence of Convolution for Visual Recognition
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision.
Ranked #765 on
Image Classification
on ImageNet
Feature-level Attentive ICF for Recommendation
To demonstrate the effectiveness of our method, we design a light attention neural network to integrate both item-level and feature-level attention for neural ICF models.
Interest-aware Message-Passing GCN for Recommendation
To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure.
Deep Texture-Aware Features for Camouflaged Object Detection
Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings.
A Unified Framework to Analyze and Design the Nonlocal Blocks for Neural Networks
When choosing Chebyshev graph filter, a generalized formulation can be derived for explaining the existing nonlocal-based blocks (e. g. nonlocal block, nonlocal stage, double attention block) and uses to analyze their irrationality.
Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias.
Ranked #1 on
Shadow Detection
on CUHK-Shadow
MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines
In this paper, we identify two main challenges that arise during the deployment of machine learning pipelines, and address them with the design of versioning for an end-to-end analytics system MLCask.
Learning to Detect Specular Highlights from Real-world Images
Specular highlight detection is a challenging problem, and has many applications such as shiny object detection and light source estimation.
Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes.
Constrained Multi-shape Evolution for Overlapping Cytoplasm Segmentation
In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump--level) modeled by considering mutual shape constraints of cytoplasms in the clump.
Task-adaptive Asymmetric Deep Cross-modal Hashing
Unlike previous cross-modal hashing approaches, our learning framework jointly optimizes semantic preserving that transforms deep features of multimedia data into binary hash codes, and the semantic regression which directly regresses query modality representation to explicit label.
Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation
Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations.
Robust Medical Instrument Segmentation Challenge 2019
The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data.
A^2-GCN: An Attribute-aware Attentive GCN Model for Recommendation
Considering the fact that for different users, the attributes of an item have different influence on their preference for this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information.
Neural Networks Weights Quantization: Target None-retraining Ternary (TNT)
Quantization of weights of deep neural networks (DNN) has proven to be an effective solution for the purpose of implementing DNNs on edge devices such as mobiles, ASICs and FPGAs, because they have no sufficient resources to support computation involving millions of high precision weights and multiply-accumulate operations.
DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning
Besides, considering the restriction of occlusion orientation presentation to occlusion orientation learning, we design a new orthogonal representation for occlusion orientation and proposed the Orthogonal Orientation Regression loss which can get rid of the unfitness between occlusion representation and learning and further prompt the occlusion orientation learning.
A Spectral Nonlocal Block for Neural Networks
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
In this paper, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision.
Distribution Matching Prototypical Network for Unsupervised Domain Adaptation
State-of-the-art Unsupervised Domain Adaptation (UDA) methods learn transferable features by minimizing the feature distribution discrepancy between the source and target domains.
Spectral Nonlocal Block for Neural Network
The nonlocal network is designed for capturing long-range spatial-temporal dependencies in several computer vision tasks.
Alleviating Feature Confusion for Generative Zero-shot Learning
An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances.
Cycle-consistent Conditional Adversarial Transfer Networks
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions.
Ranked #4 on
Domain Adaptation
on USPS-to-MNIST
Personalized Hashtag Recommendation for Micro-videos
The hashtags, that a user provides to a post (e. g., a micro-video), are the ones which in her mind can well describe the post content where she is interested in.
Enhancing Underexposed Photos using Perceptually Bidirectional Similarity
To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.
Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
This paper presents a novel framework for unsupervised 3D brain image registration by capturing the feature-level transformation relationships between the unaligned image and reference image.
Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.
From Zero-Shot Learning to Cold-Start Recommendation
This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR.
PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations.
Cross-Modal Person Re-Identification
Generative Adversarial Network
+2
Fusion-supervised Deep Cross-modal Hashing
Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages.
Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval
To address the problem, in this paper, we propose a novel hashing approach, dubbed as \emph{Discrete Semantic Transfer Hashing} (DSTH).
Discrete Optimal Graph Clustering
2) the relaxing process of cluster labels may cause significant information loss.
