Search Results for author:
Found 53 papers, 26 papers with code
Uncovering the Text Embedding in Text-to-Image Diffusion Models
The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image.
Text Data-Centric Image Captioning with Interactive Prompts
Among them, the mainstream solution is to project image embeddings into the text embedding space with the assistance of consistent representations between image-text pairs from the CLIP model.
Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features.
Accelerating Parallel Sampling of Diffusion Models
Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4~14 times.
Integrated Imaging and Communication with Reconfigurable Intelligent Surfaces
In particular, using the RIS as a wireless imaging device, our system constructs the scene depth map of the environment, including the mobile user.
ISAC with Backscattering RFID Tags: Joint Beamforming Design
Then, we study a joint beamforming design problem with the goal of minimizing the total transmit power while satisfying the tag detection and communication requirements.
CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs.
VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search
With the help of relational knowledge transfer, VGKT is capable of aligning semantic-group textual features with corresponding visual features without external tools and complex pairwise interaction.
Ranked #6 on
Text based Person Retrieval
on CUHK-PEDES
(using extra training data)
Deep Learning Enables Large Depth-of-Field Images for Sub-Diffraction-Limit Scanning Superlens Microscopy
Scanning electron microscopy (SEM) is indispensable in diverse applications ranging from microelectronics to food processing because it provides large depth-of-field images with a resolution beyond the optical diffraction limit.
Variational Quantum Linear Solver-based Combination Rules in Dempster–Shafer Theory
Dempster–Shafer Theory (DST), as a method of handling uncertain information, is widely used in decisionmaking and information fusion.
SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1% of extra parameters could surpass full fine-tuning in low-data resource scenarios.
Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval
Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR.
Boosting Unsupervised Contrastive Learning Using Diffusion-Based Data Augmentation From Scratch
When applied to biological data, DiffAug improves performance by up to 10. 1%, with an average improvement of 5. 8%.
Region Generation and Assessment Network for Occluded Person Re-Identification
Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.
Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification
In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Revisiting Vision Transformer from the View of Path Ensemble
Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and re-weight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths.
Millimeter Wave V2V Beam Tracking using Radar: Algorithms and Real-World Demonstration
Utilizing radar sensing for assisting communication has attracted increasing interest thanks to its potential in dynamic environments.
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation.
Ranked #1 on
Person Search
on PRW
CLIP4MC: An RL-Friendly Vision-Language Model for Minecraft
One of the essential missions in the AI research community is to build an autonomous embodied agent that can attain high-level performance across a wide spectrum of tasks.
Revisit Parameter-Efficient Transfer Learning: A Two-Stage Paradigm
In view of the practicality of PETL, previous works focus on tuning a small set of parameters for each downstream task in an end-to-end manner while rarely considering the task distribution shift issue between the pre-training task and the downstream task.
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance.
Ranked #8 on
Vehicle Re-Identification
on VehicleID Large
Model-Based Decentralized Policy Optimization
To help the policy improvement be stable and monotonic, we propose model-based decentralized policy optimization (MDPO), which incorporates a latent variable function to help construct the transition and reward function from an individual perspective.
A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
A Survey on Transformers in Reinforcement Learning
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings.
Good helper is around you: Attention-driven Masked Image Modeling
Most previous works mask patches of the image randomly, which underutilizes the semantic information that is beneficial to visual representation learning.
Reconfigurable Intelligent Surface Aided Wireless Sensing for Scene Depth Estimation
In this paper, we propose to employ RIS-aided wireless sensing systems for scene depth estimation.
VTC-LFC: Vision Transformer Compression with Low-Frequency Components
Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem.
MimCo: Masked Image Modeling Pre-training with Contrastive Teacher
Specifically, MimCo takes a pre-trained contrastive learning model as the teacher model and is pre-trained with two types of learning targets: patch-level and image-level reconstruction losses.
Dynamic Gradient Reactivation for Backward Compatible Person Re-identification
To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on
Unsupervised Person Re-Identification
on Market-1501
(using extra training data)
Scaled ReLU Matters for Training Vision Transformers
In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters.
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
Accelerated differential inclusion for convex optimization
This paper introduces a second-order differential inclusion for unconstrained convex optimization.
Optimization and Control 37M15, 34E10, 90C25
A primal-dual flow for affine constrained convex optimization
We introduce a novel primal-dual flow for affine constrained convex optimization problems.
Optimization and Control 37M99, 37N40, 65K05, 90C25
TransReID: Transformer-based Object Re-Identification
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on
Person Re-Identification
on Market-1501-C
1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
Counterfactual-based minority oversampling for imbalanced classification
A key challenge of oversampling in imbalanced classification is that the generation of new minority samples often neglects the usage of majority classes, resulting in most new minority sampling spreading the whole minority space.
Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor
We then propose a structure-aware network for lane marker extraction in DVS images.
Multi-Domain Learning and Identity Mining for Vehicle Re-Identification
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification
Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.
Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
In this paper, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech.
Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification
Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security.
Object Detection in Video with Spatial-temporal Context Aggregation
Without any bells and whistles, our method obtains 80. 3\% mAP on the ImageNet VID dataset, which is superior over the previous state-of-the-arts.
A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
The present study collects and evaluates these effective training tricks in person ReID.
Ranked #44 on
Person Re-Identification
on DukeMTMC-reID
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
In the literature, some effective training tricks are briefly appeared in several papers or source codes.
Ranked #2 on
Person Re-Identification
on UAV-Human
STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.
A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation
To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection.
Detect or Track: Towards Cost-Effective Video Object Detection/Tracking
Trackers are in general more efficient than detectors but bear the risk of drifting.
SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.
SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on
Person Re-Identification
on CUHK-SYSU
Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
Person re-identification (ReID) is an important task in computer vision.
