Search Results for author:
Found 104 papers, 47 papers with code
CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction
Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy.
Prompting Vision-Language Model for Nuclei Instance Segmentation and Classification
Nuclei instance segmentation and classification are a fundamental and challenging task in whole slide Imaging (WSI) analysis.
Ranked #1 on
Cell Segmentation
on MoNuSeg
$\mathbfΦ$-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data
We propose two physical loss functions: one for the generator, guiding it to produce SAR images with physical parameters consistent with real ones, and one for the discriminator, enhancing its robustness by basing decisions on PSC attributes.
Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis
As two intimate reciprocal tasks, scene-aware human motion synthesis and analysis require a joint understanding between multiple modalities, including 3D body motions, 3D scenes, and textual descriptions.
Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models
We use methods similar to those in the field of functional neuroimaging analysis to locate and identify functional networks in LLM.
CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction.
LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding
To this end, we propose a Language-Embedded Surface Field (LangSurf), which accurately aligns the 3D language fields with the surface of objects, facilitating precise 2D and 3D segmentation with text query, widely expanding the downstream tasks such as removal and editing.
PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model
PolSAR data presents unique challenges due to its rich and complex characteristics.
Physics-Guided Detector for SAR Airplanes
The main contributions of PGD include the physics-guided self-supervised learning, feature enhancement, and instance perception, denoted as PGSSL, PGFE, and PGIP, respectively.
Ranked #1 on
Object Detection
on SAR-AIRcraft-1.0
(using extra training data)
DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes
This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.
Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
To our best knowledge, this survey is the first exhaustive examination of the interdiscipline of SAR and GenAI, encompassing a wide range of topics, including deep neural networks, physical models, computer vision, and SAR images.
Brain-like Functional Organization within Large Language Models
In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain.
Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection
These type-level mamba capsules are fed into the EM routing algorithm to get the high-layer mamba capsules, which greatly reduce the computation and parameters caused by the pixel-level capsule routing for part-whole relationships exploration.
3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models
Medical image analysis is crucial in modern radiological diagnostics, especially given the exponential growth in medical imaging data.
A Survey of Foundation Models for Music Understanding
Music is essential in daily life, fulfilling emotional and entertainment needs, and connecting us personally, socially, and culturally.
Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement
Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge.
CONDA: Condensed Deep Association Learning for Co-Salient Object Detection
They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling.
X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images
The distribution inconsistency between real and simulated data is the main obstacle that influences the utility of simulated SAR images.
ASPS: Augmented Segment Anything Model for Polyp Segmentation
Polyp segmentation plays a pivotal role in colorectal cancer diagnosis.
VDG: Vision-Only Dynamic Gaussian for Driving Simulation
Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views.
Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning
Based on an empirical study on the knowledge intensity of the kernel elements of the neural network, we find that the center kernel is the key for maximizing the knowledge intensity for learning new data, while freezing the other kernel elements would get a good balance on the model's capacity for overcoming catastrophic forgetting.
Hyper-Transformer for Amodal Completion
The multi-scale features from the image branch guide the hyper transformer in learning shape priors and in generating the weights for dynamic convolution tailored to each instance.
Auto-selected Knowledge Adapters for Lifelong Person Re-identification
On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model.
Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports
The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging.
Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models' performance can be significantly improved when pre-trained with our method.
GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time
Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model.
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure.
VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
Salient object detection (SOD) and camouflaged object detection (COD) are related yet distinct binary mapping tasks.
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular.
VST++: Efficient and Stronger Visual Saliency Transformer
Our previous work, the Visual Saliency Transformer (VST), addressed this constraint from a transformer-based sequence-to-sequence perspective, to unify RGB and RGB-D SOD.
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
Physics Inspired Hybrid Attention for SAR Target Recognition
There has been a recent emphasis on integrating physical models and deep neural networks (DNNs) for SAR target recognition, to improve performance and achieve a higher level of physical interpretability.
Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation
We decompose the query video information into a clip prototype and a memory prototype for capturing local and long-term internal temporal guidance, respectively.
Chat2Brain: A Method for Mapping Open-Ended Semantic Queries to Brain Activation Maps
In this study, we propose a method called Chat2Brain that combines LLMs to basic text-2-image model, known as Text2Brain, to map open-ended semantic queries to brain activation maps in data-scarce and complex query environments.
Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning
The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances.
Ranked #1 on
Small Object Detection
on SODA-D
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules.
Ranked #1 on
Co-Salient Object Detection
on CoSal2015
ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT
The proposed method uses the strengths of LLMs' understanding and logical reasoning to correct the incomplete logical facts for optimizing the performance of perceptual module, by summarizing and reorganizing reasoning rules represented in natural language format.
Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks.
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics
We set up novel evaluation benchmarks based on a series of testing sets with evolving distributions.
Ranked #66 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt
Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels.
Fewer is More: Efficient Object Detection in Large Aerial Images
Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not.
Progressively Dual Prior Guided Few-shot Semantic Segmentation
Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples.
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
To solve this problem, we are the first to introduce an intermediate prototype for mining both deterministic category information from the support and adaptive category knowledge from the query.
Ranked #33 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Towards Large-Scale Small Object Detection: Survey and Benchmarks
Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively.
Brain Cortical Functional Gradients Predict Cortical Folding Patterns via Attention Mesh Convolution
The convolution on mesh considers the spatial organization of functional gradients and folding patterns on a cortical sheet and the newly designed channel attention block enhances the interpretability of the contribution of different functional gradients to cortical folding prediction.
Structured Attention Composition for Temporal Action Localization
To tackle this issue, we make an early effort to study temporal action localization from the perspective of multi-modality feature learning, based on the observation that different actions exhibit specific preferences to appearance or motion modality.
Learning Non-target Knowledge for Few-shot Semantic Segmentation
Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result.
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation
Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community.
Ranked #57 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Cross-Modality High-Frequency Transformer for MR Image Super-Resolution
Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.
Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.
Ranked #35 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i. e., the regions that do not need to be segmented.
Ranked #22 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Colar: Effective and Efficient Online Action Detection by Consulting Exemplars
Based on the exemplar-consultation mechanism, the long-term dependencies can be captured by regarding historical frames as exemplars, while the category-level modeling can be achieved by regarding representative frames from a category as exemplars.
Ranked #6 on
Online Action Detection
on TVSeries
Adaptive neighborhood Metric learning
In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining.
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.
Exploring Effective Data for Surrogate Training Towards Black-Box Attack
Finally, in accordance with the in-depth observations for the methods based on proxy data, we argue that leveraging the proxy data is still an effective way for surrogate training.
Robust Region Feature Synthesizer for Zero-Shot Object Detection
Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image.
Ranked #2 on
Zero-Shot Object Detection
on PASCAL VOC'07
Weakly Supervised Rotation-Invariant Aerial Object Detection Network
Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images.
Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis
Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other.
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge.
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.
Knowledge Distillation
Weakly supervised Semantic Segmentation
+1
Background-Click Supervision for Temporal Action Localization
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion.
Physically Explainable CNN for SAR Image Classification
In this paper, we first propose a novel physically explainable convolutional neural network for SAR image classification, namely physics guided and injected learning (PGIL).
Anchor-free Oriented Proposal Generator for Object Detection
Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them.
Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
On the other hand, instead of processing the twokinds of data separately, we build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns.
Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection
In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process.
Ranked #3 on
Co-Salient Object Detection
on CoSal2015
Oriented R-CNN for Object Detection
Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes.
Ranked #14 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Instance-Level Relative Saliency Ranking with Graph Reasoning
Conventional salient object detection models cannot differentiate the importance of different salient objects.
A Multi-task Deep Feature Selection Method for Brain Imaging Genetics
Though deep learning models can extract the nonlinear relationship, they could not select relevant genetic factors.
Strengthen Learning Tolerance for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as the supervision.
Large-scale Unsupervised Semantic Segmentation
In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.
Ranked #1 on
Unsupervised Semantic Segmentation
on ImageNet-S-300
Visual Saliency Transformer
We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.
Ranked #1 on
RGB-D Salient Object Detection
on NJUD
Weakly Supervised Object Localization and Detection: A Survey
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade.
Weakly Supervised Video Salient Object Detection
Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.
Densely Nested Top-Down Flows for Salient Object Detection
To this end, this paper revisits the role of top-down modeling in salient object detection and designs a novel densely nested top-down flows (DNTDF)-based framework.
Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative Guidance
In this paper, we model the information fusion within focal stack via graph networks.
Learning Dual Priors for JPEG Compression Artifacts Removal
Specifically, we design a variational model to formulate the image de-blocking problem and propose two prior terms for the image content and gradient, respectively.
Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection
Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss.
Revisiting Anchor Mechanisms for Temporal Action Localization
To address this problem, this paper proposes a novel anchor-free action localization module that assists action localization by temporal points.
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization
The existing methods can be categorized into two localization-by-classification pipelines, i. e., the pre-classification pipeline and the post-classification pipeline.
Embedded Deep Bilinear Interactive Information and Selective Fusion for Multi-view Learning
That is, we seamlessly embed various intra-view information, cross-view multi-dimension bilinear interactive information, and a new view ensemble mechanism into a unified framework to make a decision via the optimization.
Bifurcated backbone strategy for RGB-D salient object detection
In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).
Ranked #2 on
RGB-D Salient Object Detection
on RGBD135
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers.
Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate.
Robust and Efficient Fuzzy C-Means Clustering Constrained on Flexible Sparsity
Clustering is an effective technique in data mining to group a set of objects in terms of some attributes.
PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection
We propose three specific formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts.
Reinforcement Cutting-Agent Learning for Video Object Segmentation
In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework.
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
This "noisy" motion representation makes it very challenging for pose estimation and action recognition in real scenarios.
Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector
Based on this insight, we combine an intra-image fusion stream and a inter-image fusion stream in the proposed framework to generate the learning curriculum and pseudo ground-truth for supervising the training of the deep salient object detector.
PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
We formulate the proposed PiCANet in both global and local forms to attend to global and local contexts, respectively.
Ranked #7 on
RGB Salient Object Detection
on SOC
SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.
Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images
Recently, researchers have made great processes to build category-specific 3D shape models from 2D images with manual annotations consisting of class labels, keypoints, and ground truth figure-ground segmentations.
Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
Weakly-supervised object detection (WOD) is a challenging problems in computer vision.
Ranked #40 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Remote Sensing Image Scene Classification: Benchmark and State of the Art
During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images.
A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection
Furthermore, the proposed DSCLSTM model can significantly boost the saliency detection performance by incorporating both global spatial interconnections and scene context modulation, which may uncover novel inspirations for studies on them in computational saliency models.
Discriminatively Embedded K-Means for Multi-View Clustering
In real world applications, more and more data, for example, image/video data, are high dimensional and represented by multiple views which describe different perspectives of the data.
RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection
This is achieved by introducing and learning a rotation-invariant layer and a Fisher discriminative layer, respectively, on the basis of the existing high-capacity CNN architectures.
Object Co-Segmentation via Graph Optimized-Flexible Manifold Ranking
Aiming at automatically discovering the common objects contained in a set of relevant images and segmenting them as foreground simultaneously, object co-segmentation has become an active research topic in recent years.
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
Then a novel hierarchical recurrent convolutional neural network (HRCNN) is adopted to further hierarchically and progressively refine the details of saliency maps step by step via integrating local context information.
Ranked #18 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges
Co-saliency detection is a newly emerging and rapidly growing research area in computer vision community.
A Survey on Object Detection in Optical Remote Sensing Images
This paper aims to provide a review of the recent progress in this field.
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection
As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images.
Learning Coarse-to-Fine Sparselets for Efficient Object Detection and Scene Classification
Part model-based methods have been successfully applied to object detection and scene classification and have achieved state-of-the-art results.
Predicting Eye Fixations Using Convolutional Neural Networks
It is believed that eye movements in free-viewing of natural scenes are directed by both bottom-up visual saliency and top-down visual factors.
Co-Saliency Detection via Looking Deep and Wide
In the proposed framework, the wide and deep information are explored for the object proposal windows extracted in each image, and the co-saliency scores are calculated by integrating the intra-image contrast and intra group consistency via a principled Bayesian formulation.
