Search Results for author:
Found 80 papers, 42 papers with code
Statistical physics-based reconstruction in compressed sensing
Compressed sensing is triggering a major evolution in signal acquisition.
Statistical Mechanics Information Theory Information Theory
Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
We further develop the asymptotic analysis of the corresponding phase diagrams with and without measurement noise, for different distribution of signals, and discuss the best possible reconstruction performances regardless of the algorithm.
Statistical Mechanics Information Theory Information Theory
Dynamic Word Embeddings for Evolving Semantic Discovery
Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution.
SVDNet for Pedestrian Retrieval
This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID).
Ranked #14 on
Person Re-Identification
on CUHK03 detected
A Simple Approach to Learn Polysemous Word Embeddings
Evaluating these methods is also problematic, as rigorous quantitative evaluations in this space is limited, especially when compared with single-sense embeddings.
Straggler Mitigation in Distributed Optimization Through Data Encoding
Slow running or straggler tasks can significantly reduce computation speed in distributed computation.
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
Deep Unsupervised Clustering Using Mixture of Autoencoders
Unsupervised clustering is one of the most fundamental challenges in machine learning.
Wide Compression: Tensor Ring Nets
Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications.
Redundancy Techniques for Straggler Mitigation in Distributed Optimization and Learning
Performance of distributed optimization and learning systems is bottlenecked by "straggler" nodes and slow communication links, which significantly delay computation.
Joint Map and Symmetry Synchronization
Most existing techniques in map computation (e. g., in the form of feature or dense correspondences) assume that the underlying map between an object pair is unique.
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).
Ranked #14 on
Person Re-Identification
on Market-1501-C
Learning low-dimensional state embeddings and metastable clusters from time series data
This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank.
NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
We propose a neural network based approach for extracting models from dynamic data using ordinary and partial differential equations.
Ranked #12 on
Image Classification
on Fashion-MNIST
K-Best Transformation Synchronization
In this paper, we introduce the problem of K-best transformation synchronization for the purpose of multiple scan matching.
Vehicle Re-identification with Viewpoint-aware Metric Learning
This paper considers vehicle re-identification (re-ID) problem.
Safe Screening for the Generalized Conditional Gradient Method
The conditional gradient method (CGM) has been widely used for fast sparse approximation, having a low per iteration computational cost for structured sparse regularizers.
Circle Loss: A Unified Perspective of Pair Similarity Optimization
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity.
Embodied Self-supervised Learning by Coordinated Sampling and Training
The proposed approach works in an analysis-by-synthesis manner to learn an inference network by iteratively sampling and training.
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i. e.}, deep image classification and deep metric learning (on long-tailed data).
Ranked #44 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Latent Group Structured Multi-task Learning
In multi-task learning (MTL), we improve the performance of key machine learning algorithms by training various tasks jointly.
Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
%We argue that such flexibility is also important for deep metric learning, because different visual concepts indeed correspond to different semantic scales.
Ranked #2 on
Metric Learning
on DyML-Animal
Learning View Selection for 3D Scenes
Efficient 3D space sampling to represent an underlying3D object/scene is essential for 3D vision, robotics, and be-yond.
Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets
In this paper, we consider approximate Frank-Wolfe (FW) algorithms to solve convex optimization problems over graph-structured support sets where the linear minimization oracle (LMO) cannot be efficiently obtained in general.
Screening for a Reweighted Penalized Conditional Gradient Method
We couple this with a screening rule which is safe in the convex case, converging to the true support at a rate $O(1/(\delta^2))$ where $\delta \geq 0$ measures how close the problem is to degeneracy.
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.
Domain Adaptive Person Re-Identification
Person Re-Identification
Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification
We hold a hypothesis, i. e., if a deep model is capable to fast generalize itself to different domains (using very few samples) during training, it will maintain such domain generalization capacity for testing.
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student.
D$^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21.
Bag of Tricks and A Strong baseline for Image Copy Detection
In this paper, a bag of tricks and a strong baseline are proposed for image copy detection.
Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
MFA basically considers three parallel information fusion strategies, i. e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion.
Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval
By combining two fundamental learning approaches in DML, e. g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR.
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection
How to align the source and target domains is critical to the CDWSOD accuracy.
Ranked #1 on
Weakly Supervised Object Detection
on Clipart1k
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
Action Keypoint Network for Efficient Video Recognition
An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods.
Ranked #42 on
Action Recognition
on Something-Something V1
Results and findings of the 2021 Image Similarity Challenge
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
Enhancing Continual Learning with Global Prototypes: Counteracting Negative Representation Drift
Continual learning (CL) aims to learn a sequence of tasks over time, with data distributions shifting from one task to another.
Accelerating Frank-Wolfe via Averaging Step Directions
The Frank-Wolfe method is a popular method in sparse constrained optimization, due to its fast per-iteration complexity.
A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i. e., there is a fundamental conflict between current metric learning and ICD.
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
Our novel sparse feature sampling module only utilizes local 2D region of interest (RoI) features calculated by the projection of 3D query boxes for further box refinement, leading to a fully-convolutional and deployment-friendly pipeline.
Ranked #8 on
Robust Camera Only 3D Object Detection
on nuScenes-C
UFO: Unified Feature Optimization
UFO aims to benefit each single task with a large-scale pretraining on all tasks.
V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval
While model ensemble is common, we show that combining the vision models and vision-language models brings particular benefits from their complementarity and is a key factor to our superiority.
Feature-Proxy Transformer for Few-Shot Segmentation
With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.
A Multistep Frank-Wolfe Method
The Frank-Wolfe algorithm has regained much interest in its use in structurally constrained machine learning applications.
Generalizable Re-Identification from Videos with Cycle Association
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos.
Domain Generalization
Generalizable Person Re-identification
+1
Clustered Federated Learning based on Nonconvex Pairwise Fusion
We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters.
Semisoft Task Clustering for Multi-Task Learning
Motivated by the idea of semisoft clustering of data, we propose a semisoft task clustering approach, which can simultaneously reveal the task cluster structure for both pure and mixed tasks as well as select the relevant features.
An adaptive shortest-solution guided decimation approach to sparse high-dimensional linear regression
High-dimensional linear regression model is the most popular statistical model for high-dimensional data, but it is quite a challenging task to achieve a sparse set of regression coefficients.
ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification
Based on these two common practices, the key point of ProD is using the prompting mechanism in the transformer to disentangle the domain-general (DG) and domain-specific (DS) knowledge from the backbone feature.
Context-Aware Pretraining for Efficient Blind Image Decomposition
(2) The conventional paradigm usually focuses on mining the abnormal pattern of a superimposed image to separate the noise, which de facto conflicts with the primary image restoration task.
Pose Synchronization Under Multiple Pair-Wise Relative Poses
The first step performs diffusion and clustering to compute the candidate poses of the input objects.
MMA-RNN: A Multi-level Multi-task Attention-based Recurrent Neural Network for Discrimination and Localization of Atrial Fibrillation
The automatic detection of atrial fibrillation based on electrocardiograph (ECG) signals has received wide attention both clinically and practically.
Unsupervised Facial Expression Representation Learning with Contrastive Local Warping
Therefore, given a facial image, ContraWarping employs some global transformations and local warping to generate its positive and negative samples and sets up a novel contrastive learning framework.
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble.
Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis
This paper explores an expression-related self-supervised learning (SSL) method (ContraWarping) to perform expression classification in the 5th Affective Behavior Analysis in-the-wild (ABAW) competition.
Reducing Discretization Error in the Frank-Wolfe Method
The Frank-Wolfe algorithm is a popular method in structurally constrained machine learning applications, due to its fast per-iteration complexity.
TransHP: Image Classification with Hierarchical Prompting
This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task.
DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection
Second, through our design, the object queries and the foreground query in the decoder share consensus on the class semantics, therefore making the strong and weak supervision mutually benefit each other for domain alignment.
Feature-compatible Progressive Learning for Video Copy Detection
Video Copy Detection (VCD) has been developed to identify instances of unauthorized or duplicated video content.
On the Difficulty of Intersection Checking with Polynomial Zonotopes
The standard method for intersection checking with polynomial zonotopes is a two-part algorithm that overapproximates a polynomial zonotope with a regular zonotope and then, if the overapproximation error is deemed too large, splits the set and recursively tries again.
GUARD: A Safe Reinforcement Learning Benchmark
Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms.
Fast Online Node Labeling for Very Large Graphs
This paper studies the online node classification problem under a transductive learning setting.
Whitening-based Contrastive Learning of Sentence Embeddings
Consequently, using multiple positive samples with enhanced diversity further improves contrastive learning due to better alignment.
Jigsaw: Learning to Assemble Multiple Fractured Objects
Our framework consists of four components: (1) front-end point feature extractor with attention layers, (2) surface segmentation to separate fracture and original parts, (3) multi-parts matching to find correspondences among fracture surface points, and (4) robust global alignment to recover the global poses of the pieces.
State-wise Constrained Policy Optimization
In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO.
Large-Scale Person Detection and Localization using Overhead Fisheye Cameras
Instead of existing efforts devoted to localizing tourist photos captured by perspective cameras, in this article, we focus on devising person positioning solutions using overhead fisheye cameras.
A Lightweight and Transferable Design for Robust LEGO Manipulation
Experiments demonstrate that the EOAT can reliably manipulate Lego bricks and the learning framework can effectively and safely improve the manipulation performance to a 100% success rate.
Absolute Policy Optimization
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios.
Data Acquisition: A New Frontier in Data-centric AI
As Machine Learning (ML) systems continue to grow, the demand for relevant and comprehensive datasets becomes imperative.
Real-time Estimation of DoS Duration and Frequency for Security Control
In this paper, we develop a new denial-of-service (DoS) estimator, enabling defenders to identify duration and frequency parameters of any DoS attacker, except for three edge cases, exclusively using real-time data.
On Mask-based Image Set Desensitization with Recognition Support
In addition, we propose a feature selection masknet as the model adjustment method to improve the performance based on the masked images.
Understanding News Creation Intents: Frame, Dataset, and Method
As the disruptive changes in the media economy and the proliferation of alternative news media outlets, news intent has progressively deviated from ethical standards that serve the public interest.
Representation of forward performance criteria with random endowment via FBSDE and application to forward optimized certainty equivalent
We, also, consider representative examples for both forward performance criteria with random endowment and forward OCE, and for the case of exponential criteria, we investigate the connection between forward OCE and forward entropic risk measures.
MS-DETR: Efficient DETR Training with Mixed Supervision
The traditional training procedure using one-to-one supervision in the original DETR lacks direct supervision for the object detection candidates.
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts.
AnyPattern: Towards In-context Image Copy Detection
This paper explores in-context learning for image copy detection (ICD), i. e., prompting an ICD model to identify replicated images with new tampering patterns without the need for additional training.
Multiplex Anti-Asian Sentiment before and during the Pandemic: Introducing New Datasets from Twitter Mining
We introduce new datasets from Twitter related to anti-Asian hate sentiment before and during the pandemic.
