Search Results for author:
Found 74 papers, 26 papers with code
Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.
Ranked #6 on
Multi-Label Classification
on NUS-WIDE
Attention-Aware Compositional Network for Person Re-identification
AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC).
Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning
We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1. 39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space.
AUTOHOME-ORCA at SemEval-2019 Task 8: Application of BERT for Fact-Checking in Community Forums
In order to address this task, we propose a system based on the BERT model with meta information of questions.
Towards Unified INT8 Training for Convolutional Neural Network
In this paper, we give an attempt to build a unified 8-bit (INT8) training framework for common convolutional neural networks from the aspects of both accuracy and speed.
Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.
Ranked #4 on
Unsupervised Domain Adaptation
on Market to MSMT
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory.
Ranked #3 on
Unsupervised Domain Adaptation
on Market to MSMT
Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset.
Understanding the effect of hyperparameter optimization on machine learning models for structure design problems
After HOpt, the training cost of ANN and RFR is increased more than that of the GPR and SVM.
A Deep Framework for Cross-Domain and Cross-System Recommendations
Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy.
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
However, the inversion process only utilizes biased feature statistics stored in one model and is from low-dimension to high-dimension.
Progressive Correspondence Pruning by Consensus Learning
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences.
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations
The MolMapNet learned important features that are consistent with the literature-reported molecular features.
Cross-Domain Recommendation: Challenges, Progress, and Prospects
To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain.
Minimization of ion micromotion with artificial neural network
Minimizing the micromotion of the single trapped ion in a linear Paul trap is a tedious and time-consuming work, but is of great importance in cooling the ion into the motional ground state as well as maintaining long coherence time, which is crucial for quantum information processing and quantum computation.
Atomic Physics Quantum Physics
Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
In this way, our BAKE framework achieves online knowledge ensembling across multiple samples with only a single network.
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms.
Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts.
Improving Facial Attribute Recognition by Group and Graph Learning
For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature.
Offline Planning and Online Learning under Recovering Rewards
Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the decision maker can pull and collect rewards from up to $K\,(\ge 1)$ out of $N$ different arms in each time period; (ii) the expected reward of an arm immediately drops after it is pulled, and then non-parametrically recovers as the arm's idle time increases.
A new method for vehicle system safety design based on data mining with uncertainty modeling
In this research, a new data mining-based design approach has been developed for designing complex mechanical systems such as a crashworthy passenger car with uncertainty modeling.
A Unified Framework for Cross-Domain and Cross-System Recommendations
Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i. e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively.
Temporal RoI Align for Video Object Recognition
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on
Video Instance Segmentation
on YouTube-VIS
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
Improving the Transferability of Supervised Pretraining with an MLP Projector
The pretrain-finetune paradigm is a classical pipeline in visual learning.
Real-time, low-cost multi-person 3D pose estimation
The process of tracking human anatomy in computer vision is referred to pose estimation, and it is used in fields ranging from gaming to surveillance.
Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time
We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data.
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
The pretrain-finetune paradigm is a classical pipeline in visual learning.
DronePose: The identification, segmentation, and orientation detection of drones via neural networks
The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles.
Feature Erasing and Diffusion Network for Occluded Person Re-Identification
With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics.
Ranked #1 on
Person Re-Identification
on Occluded REID
(Rank-1 metric)
GPS: A Policy-driven Sampling Approach for Graph Representation Learning
Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks.
Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification
These two unidirectional metrics (IR image to RGB proxy and RGB image to IR proxy) jointly alleviate the relay effect and benefit cross-modality association.
Cross-Modality Person Re-identification
Person Re-Identification
Align Representations With Base: A New Approach to Self-Supervised Learning
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
Adaptive Worker Grouping For Communication-Efficient and Straggler-Tolerant Distributed SGD
Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings.
Time Dependency, Data Flow, and Competitive Advantage
Relating the text topics to various business areas of interest, we argue that competing in a business area in which data value decays rapidly alters strategies to acquire competitive advantage.
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
Scalability is an important consideration for deep graph neural networks.
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.
A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Stochastic Bandits
Starting from the two-armed bandit setting with time horizon $T$, we propose a simple policy and prove that the policy (i) enjoys the worst-case optimality for the expected regret at order $O(\sqrt{T\ln T})$ and (ii) has the worst-case tail probability of incurring a linear regret decay at an exponential rate $\exp(-\Omega(\sqrt{T}))$, a rate that we prove to be best achievable for all worst-case optimal policies.
LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud
Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration.
Modeling Adaptive Platoon and Reservation Based Autonomous Intersection Control: A Deep Reinforcement Learning Approach
As a strategy to reduce travel delay and enhance energy efficiency, platooning of connected and autonomous vehicles (CAVs) at non-signalized intersections has become increasingly popular in academia.
COOR-PLT: A hierarchical control model for coordinating adaptive platoons of connected and autonomous vehicles at signal-free intersections based on deep reinforcement learning
The simulation results demonstrate that the model is able to: (1) achieve satisfactory convergence performances; (2) adaptively determine platoon size in response to varying traffic conditions; and (3) completely avoid deadlocks at the intersection.
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task.
Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way.
BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
To address this limitation, we present a novel Bag of Words for real-time loop closing in 3D LiDAR SLAM, called BoW3D.
STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization
Synchronous local stochastic gradient descent (local SGD) suffers from some workers being idle and random delays due to slow and straggling workers, as it waits for the workers to complete the same amount of local updates.
Simulating single-photon detector array sensors for depth imaging
Our approach accurately generates realistic depth images in a wide range of scenarios, allowing the performance of an optical depth imaging system to be established without the need for costly and laborious field testing.
Locating Noise is Halfway Denoising for Semi-Supervised Segmentation
This work shows that locating the patch-wise noisy region is a better way to deal with noise.
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision
Meanwhile, SANE easily establishes multi-task learning with CORE loss functions on both depth and surface normal estimation, leading to the whole performance leap.
DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
Saliency Guided Contrastive Learning on Scene Images
Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.
UniHCP: A Unified Model for Human-Centric Perceptions
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
Ranked #1 on
Pose Estimation
on MS-COCO
HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Ranked #1 on
Pedestrian Attribute Recognition
on PA-100K
(using extra training data)
CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
To overcome these obstacles, we propose CORA, a DETR-style framework that adapts CLIP for Open-vocabulary detection by Region prompting and Anchor pre-matching.
Ranked #6 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference
To address this issue, we collect a dataset of human choices on generated images from the Stable Foundation Discord channel.
Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk
A novel policy is proposed to characterize the optimal regret tail probability for any regret threshold.
Advancing Referring Expression Segmentation Beyond Single Image
To overcome this limitation, we propose a more realistic and general setting, named Group-wise Referring Expression Segmentation (GRES), which expands RES to a collection of related images, allowing the described objects to be present in a subset of input images.
Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
By fine-tuning CLIP on HPD v2, we obtain Human Preference Score v2 (HPS v2), a scoring model that can more accurately predict human preferences on generated images.
Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
Referential dialogue is a superset of various vision-language (VL) tasks.
Ranked #10 on
Visual Question Answering
on ViP-Bench
Described Object Detection: Liberating Object Detection with Flexible Expressions
In this paper, we advance them to a more practical setting called Described Object Detection (DOD) by expanding category names to flexible language expressions for OVD and overcoming the limitation of REC only grounding the pre-existing object.
Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences.
Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering.
Link-Context Learning for Multimodal LLMs
The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations.
Freshness or Accuracy, Why Not Both? Addressing Delayed Feedback via Dynamic Graph Neural Networks
In the model training, we propose a novel graph convolutional method named HLGCN, which leverages both high-pass and low-pass filters to deal with conversion and non-conversion relationships.
DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data
Local stochastic gradient descent (SGD) is a fundamental approach in achieving communication efficiency in Federated Learning (FL) by allowing individual workers to perform local updates.
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
In order to encompass common detection expressions, we involve emerging vision-language model (VLM) and large language model (LLM) to generate instructions guided by text prompts and object bbxs, as the generalizations of foundation models are effective to produce human-like expressions (e. g., describing object property, category, and relationship).
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
Ranked #1 on
Pedestrian Image Caption
on CUHK-PEDES
VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network
Trajectory recovery based on the snapshots from the city-wide multi-camera network facilitates urban mobility sensing and driveway optimization.
Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies
The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities.
Online Local False Discovery Rate Control: A Resource Allocation Approach
We start with general arrival distributions and show that a simple policy achieves a $O(\sqrt{T})$ regret.
3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis
In this way, our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction.
Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation
As a result, dual-target CDR has to meet two challenges: (1) how to effectively decouple observed confounders, including single-domain confounders and cross-domain confounders, and (2) how to preserve the positive effects of observed confounders on predicted interactions, while eliminating their negative effects on capturing comprehensive user preferences.
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment
Finally, we consider an analogous non-stationary setting in the canonical multi-armed bandit problem, and points out that the \textit{any-time} situation and the \textit{fixed-time} situation render the same optimal regret order in a simple form, in contrast to the dynamic pricing problem.
