Search Results for author:
Found 103 papers, 39 papers with code
Mask and Regenerate: A Classifier-based Approach for Unpaired Sentiment Transformation of Reviews for Electronic Commerce Websites.
Specifically, we train a multilayer perceptron (MLP) as a style classifier to find out and mask style-characteristic words in the source inputs.
Video Summarization using Denoising Diffusion Probabilistic Model
Specifically, we propose a novel diffusion summarization method based on the Denoising Diffusion Probabilistic Model (DDPM), which learns the probability distribution of training data through noise prediction, and generates summaries by iterative denoising.
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
Compared with unsupervised SoTA models, RAZOR improves by 3. 5% on the FEVER and 6. 5% on MNLI and SNLI datasets according to the F1 score.
BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching
Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications.
Multimodal Commonsense Knowledge Distillation for Visual Question Answering
Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in the general Visual Question Answering (VQA).
A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization
Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data.
SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity
To address these issues, we propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation.
Towards Edge General Intelligence via Large Language Models: Opportunities and Challenges
The integration of Large Language Models (LLMs) empowers EI to evolve into the next stage: Edge General Intelligence (EGI), enabling more adaptive and versatile applications that require advanced understanding and reasoning capabilities.
Is Parameter Collision Hindering Continual Learning in LLMs?
Large Language Models (LLMs) often suffer from catastrophic forgetting when learning multiple tasks sequentially, making continual learning (CL) essential for their dynamic deployment.
AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation
Extensive experiments on two real-world datasets validate that our AlignGroup outperforms the state-of-the-art on both the group recommendation task and the user recommendation task, as well as outperforms the efficiency of most baselines.
Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems.
A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model
The results show that the proposed algorithm can generate safe and reasonable actions in a variety of complex scenarios and guarantee safety without losing the evolutionary potential of learning-based autonomous driving systems.
A Safe and Efficient Self-evolving Algorithm for Decision-making and Control of Autonomous Driving Systems
Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment.
Post-Training Sparse Attention with Double Sparsity
Our key insight is that the pattern of channel sparsity is relatively static, allowing us to use offline calibration to make it efficient at runtime, thereby enabling accurate and efficient identification of important tokens.
Assessment of Continuous-Time Transmission-Distribution-Interface Active and Reactive Flexibility for Flexible Distribution Networks
This model comprehensively considers the flexible devices in the FDN and the impact of uncertainty of photovoltaic power generation and load.
P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models
A multitude of industries depend on accurate and reasonable tabular data augmentation for their business processes.
FourierKAN-GCF: Fourier Kolmogorov-Arnold Network -- An Effective and Efficient Feature Transformation for Graph Collaborative Filtering
We revisit these two components and discover that a part of feature transformation and nonlinear operation during message passing in GCN can improve the representation of GCF, but increase the difficulty of training.
Matrix Manifold Neural Networks++
Recently, some works have shown that many concepts in the theory of gyrogroups and gyrovector spaces can also be generalized to matrix manifolds such as Symmetric Positive Definite (SPD) and Grassmann manifolds.
Enhancing Content-based Recommendation via Large Language Model
However, they still neglect the following two points: (1) The content semantic is a universal world knowledge; how do we extract the multi-aspect semantic information to empower different domains?
Conformal Off-Policy Prediction for Multi-Agent Systems
A key contribution of MA-COPP is to avoid enumeration or exhaustive search of the output space of agent trajectories, which is instead required by existing COPP methods to construct the prediction region.
Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning
This paper proposes a novel framework for multi-label image recognition without any training data, called data-free framework, which uses knowledge of pre-trained Large Language Model (LLM) to learn prompts to adapt pretrained Vision-Language Model (VLM) like CLIP to multilabel classification.
MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation
It utilizes multimodal information to alleviate the data sparsity problem in recommendation systems, thus improving recommendation accuracy.
Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
This research significantly reduces training costs of proximal policy-guided models and demonstrates the potential for self-correction of language models.
PiCO: Peer Review in LLMs based on the Consistency Optimization
Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations.
Data-efficient Fine-tuning for LLM-based Recommendation
To pursue the two objectives, we propose a novel data pruning method based on two scores, i. e., influence score and effort score, to efficiently identify the influential samples.
Learning Local Control Barrier Functions for Hybrid Systems
Our approach is computationally efficient, minimally invasive to any reference controller, and applicable to large-scale systems.
Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction
In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between "easy" and "hard" samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish "hard" samples in a fine-grained manner.
Rethinking Benchmark and Contamination for Language Models with Rephrased Samples
Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets.
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
To capitalize on these opportunities, we present S-LoRA, a system designed for the scalable serving of many LoRA adapters.
Learning Adaptive Safety for Multi-Agent Systems
Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents.
Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications
The STL requirements are designed to include both task specifications according to the objective of each agent and safety specifications, and the robustness values of the STL specifications are leveraged to generate rewards.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+1
Large-scale Dataset Pruning with Dynamic Uncertainty
The state of the art of many learning tasks, e. g., image classification, is advanced by collecting larger datasets and then training larger models on them.
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach
Recently, by applying the theory of gyrogroups and gyrovector spaces that is a powerful framework for studying hyperbolic geometry, some works have attempted to build principled generalizations of Euclidean neural networks on matrix manifolds.
Revisiting Context Aggregation for Image Matting
Furthermore, AEMatter leverages a large image training strategy to assist the network in learning context aggregation from data.
Ranked #1 on
Image Matting
on Composition-1K
Safe Perception-Based Control under Stochastic Sensor Uncertainty using Conformal Prediction
However, these perception maps are not perfect and result in state estimation errors that can lead to unsafe system behavior.
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
Cross-modal retrieval with noisy correspondence
Image-text matching
+1
MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts
In this paper, we propose MEGA-DAgger, a new DAgger variant that is suitable for interactive learning with multiple imperfect experts.
Rethink Long-tailed Recognition with Vision Transformers
Hence, we propose to adopt unsupervised learning to utilize long-tailed data.
MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions.
PPR: Physically Plausible Reconstruction from Monocular Videos
Given monocular videos, we build 3D models of articulated objects and environments whose 3D configurations satisfy dynamics and contact constraints.
Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation
Besides, we also verify that the proposed framework is able to explicitly control the emotion of the animated talking face.
CPMLHO:Hyperparameter Tuning via Cutting Plane and Mixed-Level Optimization
The bilevel optimization is used to automatically update the hyperparameter, and the gradient of the hyperparameter is the approximate gradient based on the best response function.
Learning Imbalanced Data with Vision Transformers
In this paper, we systematically investigate the ViTs' performance in LTR and propose LiVT to train ViTs from scratch only with LT data.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
You Don't Know When I Will Arrive: Unpredictable Controller Synthesis for Temporal Logic Tasks
This problem is particularly challenging since future information is involved in the synthesis process.
Towards Regression-Free Neural Networks for Diverse Compute Platforms
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important.
Differentiable Safe Controller Design through Control Barrier Functions
Learning-based controllers, such as neural network (NN) controllers, can show high empirical performance but lack formal safety guarantees.
Toward Understanding Privileged Features Distillation in Learning-to-Rank
Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item" as a feature is predictive of "user purchased this item" in the offline data, but is clearly not available during online serving.
Gaia: Graph Neural Network with Temporal Shift aware Attention for Gross Merchandise Value Forecast in E-commerce
E-commerce has gone a long way in empowering merchants through the internet.
Dataset Pruning: Reducing Training Data by Examining Generalization Influence
To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap.
Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos
Language-driven action localization in videos is a challenging task that involves not only visual-linguistic matching but also action boundary prediction.
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training
Based on the observation, we present a method, called Ensemble Logit Difference Inhibition (ELODI), to train a classification system that achieves paragon performance in both error rate and NFR, at the inference cost of a single model.
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
CAFE: Learning to Condense Dataset by Aligning Features
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.
An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022
Temporal link prediction, as one of the most crucial work in temporal graphs, has attracted lots of attention from the research area.
Sample Efficiency of Data Augmentation Consistency Regularization
Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to use augmented data.
Semantically Contrastive Learning for Low-light Image Enhancement
Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images.
PartImageNet: A Large, High-Quality Dataset of Parts
To help address this problem, we propose PartImageNet, a large, high-quality dataset with part segmentation annotations.
Does Preprocessing Help Training Over-parameterized Neural Networks?
The classical training method requires paying $\Omega(mnd)$ cost for both forward computation and backward computation, where $m$ is the width of the neural network, and we are given $n$ training points in $d$-dimensional space.
Speeding up Deep Model Training by Sharing Weights and Then Unsharing
Our approach exploits the special structure of BERT that contains a stack of repeated modules (i. e., transformer encoders).
Objects in Semantic Topology
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
Theoretical Analysis of Consistency Regularization with Limited Augmented Data
Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to use augmented data.
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker.
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i. e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels.
Compatibility-aware Heterogeneous Visual Search
Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images.
An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
Moreover, we generate a cheap heatmap based on the face alignment result and fuse it with features to improve the performance of the other two tasks.
Ranked #28 on
Face Alignment
on WFLW
Combinatorial Bandits without Total Order for Arms
Specifically, we focus on a challenging setting where 1) the reward distribution of an arm depends on the set $s$ it is part of, and crucially 2) there is \textit{no total order} for the arms in $\mathcal{A}$.
Linear Bandit Algorithms with Sublinear Time Complexity
For sufficiently large $K$, our algorithms have sublinear per-step complexity and $\tilde O(\sqrt{T})$ regret.
CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects.
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
Free Lunch for Few-shot Learning: Distribution Calibration
In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples, then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier.
Unsupervised Word Alignment via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
Speeding up Deep Learning Training by Sharing Weights and Then Unsharing
It has been widely observed that increasing deep learning model sizes often leads to significant performance improvements on a variety of natural language processing and computer vision tasks.
Real-space construction of crystalline topological superconductors and insulators in 2D interacting fermionic systems
The construction and classification of crystalline symmetry protected topological (SPT) phases in interacting bosonic and fermionic systems have been intensively studied in the past few years.
Strongly Correlated Electrons Mesoscale and Nanoscale Physics Mathematical Physics Mathematical Physics
The ANTARES Astronomical Time-Domain Event Broker
We describe the Arizona-NOIRLab Temporal Analysis and Response to Events System (ANTARES), a software instrument designed to process large-scale streams of astronomical time-domain alerts.
Instrumentation and Methods for Astrophysics
Positive-Congruent Training: Towards Regression-Free Model Updates
Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error.
SMOT: Single-Shot Multi Object Tracking
We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module.
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.
Single-View 3D Object Reconstruction from Shape Priors in Memory
Inspired by this, we propose a novel method, named Mem3D, that explicitly constructs shape priors to supplement the missing information in the image.
Adaptive Semantic-Visual Tree for Hierarchical Embeddings
To solve this new problem, we propose a hierarchical adaptive semantic-visual tree (ASVT) to depict the architecture of merchandise categories, which evaluates semantic similarities between different semantic levels and visual similarities within the same semantic class simultaneously.
Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space
In this paper, we provide a new algorithm - Interaction Hard Thresholding (IntHT) which is the first one to provably accurately solve this problem in sub-quadratic time and space.
FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos
A structure predictor is proposed to predict the missing face structural information temporally, which serves as a geometry prior.
Learning Actions from Human Demonstration Video for Robotic Manipulation
However, the general video captioning methods focus more on the understanding of the full frame, lacking of consideration on the specific object of interests in robotic manipulations.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Region Proposal by Guided Anchoring
State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.
Ranked #1 on
Region Proposal
on COCO test-dev
Effective Learning of Probabilistic Models for Clinical Predictions from Longitudinal Data
It also demonstrates the outstanding performance of these proposed models as well as other state of the art machine learning models when applied to medical research problems and other real-world large-scale systems, reveals the great potential of statistical relational learning for exploring the structured health-related data to facilitate medical research.
Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling
We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful.
Look at Boundary: A Boundary-Aware Face Alignment Algorithm
By utilising boundary information of 300-W dataset, our method achieves 3. 92% mean error with 0. 39% failure rate on COFW dataset, and 1. 25% mean error on AFLW-Full dataset.
Ranked #4 on
Face Alignment
on AFLW-19
(using extra training data)
Optimizing Video Object Detection via a Scale-Time Lattice
High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e. g. those that require detecting objects from video streams in real time.
Leveraging intra and inter-dataset variations for robust face alignment
Face alignment is a critical topic in the computer vision community.
Ranked #35 on
Face Alignment
on WFLW
Face Detection through Scale-Friendly Deep Convolutional Networks
Specifically, our method achieves 76. 4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.
Residual Attention Network for Image Classification
In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion.
Ranked #684 on
Image Classification
on ImageNet
Hand3D: Hand Pose Estimation using 3D Neural Network
We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image.
Faceness-Net: Face Detection through Deep Facial Part Responses
We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision.
Joint Hand Detection and Rotation Estimation by Using CNN
Hand detection is essential for many hand related tasks, e. g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction.
Application of Statistical Relational Learning to Hybrid Recommendation Systems
In this paper, we proposed a way to adapt the state-of-the-art in SRL learning approaches to construct a real hybrid recommendation system.
WIDER FACE: A Face Detection Benchmark
Face detection is one of the most studied topics in the computer vision community.
Ranked #34 on
Face Detection
on WIDER Face (Medium)
From Facial Parts Responses to Face Detection: A Deep Learning Approach
In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW.
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.
