Search Results for author:
Found 151 papers, 49 papers with code
Task Understanding from Confusing Multi-task Data
Beyond machine learning's success in the specific tasks, research for learning multiple tasks simultaneously is referred to as multi-task learning.
Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
To explore this, we focus on pass@N, a simple test-time strategy that searches for a correct answer in $N$ independent samples.
ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality
By decoding multiple tokens simultaneously in a single forward pass, the number of forward passes required to generate an image is significantly reduced, resulting in a substantial improvement in generation efficiency.
Evaluating and Advancing Multimodal Large Language Models in Ability Lens
To address this, we introduce \textbf{AbilityLens}, a unified benchmark designed to evaluate MLLMs across six key perception abilities, focusing on both accuracy and stability, with each ability encompassing diverse question types, domains, and metrics.
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks.
Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalization
Open-set domain generalization addresses a real-world challenge: training a model to generalize across unseen domains (domain generalization) while also detecting samples from unknown classes not encountered during training (open-set recognition).
KMM: Key Frame Mask Mamba for Extended Motion Generation
The recent Mamba architecture shows promising results in efficiently modeling long and complex sequences, yet two significant challenges remain: Firstly, directly applying Mamba to extended motion generation is ineffective, as the limited capacity of the implicit memory leads to memory decay.
Fair In-Context Learning via Latent Concept Variables
However, with increasing applications in high-stakes domains, it has been shown that LLMs can inherit social bias and discrimination from their pre-training data.
MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning
Extensive experiments on real-world and synthetic datasets demonstrate MADOD's superior performance in semantic OOD detection across unseen domains, achieving an AUPR improvement of 8. 48% to 20. 81%, while maintaining competitive in-distribution classification accuracy, representing a significant advancement in handling both covariate and semantic shifts.
FEED: Fairness-Enhanced Meta-Learning for Domain Generalization
Generalizing to out-of-distribution data while being aware of model fairness is a significant and challenging problem in meta-learning.
Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications.
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase, particularly in scenarios involving high-resolution images or videos.
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets.
On the Evaluation of Generative Robotic Simulations
For single-task quality, we evaluate the realism of the generated task and the completeness of the generated trajectories using large language models and vision-language models.
Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion
To address the problem of ``cross-dataset gaze estimation'', we propose a novel Evidential Inter-intra Fusion EIF framework, for training a cross-dataset model that performs well across all source and unseen domains.
IAFI-FCOS: Intra- and across-layer feature interaction FCOS model for lesion detection of CT images
Effective lesion detection in medical image is not only rely on the features of lesion region, but also deeply relative to the surrounding information. However, most current methods have not fully utilize it. What is more, multi-scale feature fusion mechanism of most traditional detectors are unable to transmit detail information without loss, which makes it hard to detect small and boundary ambiguous lesion in early stage disease. To address the above issues, we propose a novel intra- and across-layer feature interaction FCOS model (IAFI-FCOS) with a multi-scale feature fusion mechanism ICAF-FPN, which is a network structure with intra-layer context augmentation (ICA) block and across-layer feature weighting (AFW) block. Therefore, the traditional FCOS detector is optimized by enriching the feature representation from two perspectives. Specifically, the ICA block utilizes dilated attention to augment the context information in order to capture long-range dependencies between the lesion region and the surrounding. The AFW block utilizes dual-axis attention mechanism and weighting operation to obtain the efficient across-layer interaction features, enhancing the representation of detailed features. Our approach has been extensively experimented on both the private pancreatic lesion dataset and the public DeepLesion dataset, our model achieves SOTA results on the pancreatic lesion dataset.
LSM-YOLO: A Compact and Effective ROI Detector for Medical Detection
Firstly, by using LAE to refine feature extraction, the model can obtain more contextual information and high-resolution details from multiscale feature maps, thereby extracting detailed features of ROI in medical images while reducing the influence of noise.
Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data
Text-to-video (T2V) generation has gained significant attention due to its wide applications to video generation, editing, enhancement and translation, \etc.
HQOD: Harmonious Quantization for Object Detection
Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks.
InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation
Text-to-motion generation holds potential for film, gaming, and robotics, yet current methods often prioritize short motion generation, making it challenging to produce long motion sequences effectively: (1) Current methods struggle to handle long motion sequences as a single input due to prohibitively high computational cost; (2) Breaking down the generation of long motion sequences into shorter segments can result in inconsistent transitions and requires interpolation or inpainting, which lacks entire sequence modeling.
Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations
Implicit bias can impede patient-provider interactions and lead to inequities in care.
Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?
Text summarization, a key natural language generation (NLG) task, is vital in various domains.
GMT: Guided Mask Transformer for Leaf Instance Segmentation
Leaf instance segmentation is a challenging multi-instance segmentation task, aiming to separate and delineate each leaf in an image of a plant.
PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge
Our approach achieved the 1st position in the Hand Pose challenge with 25. 51 MPJPE and 8. 49 PA-MPJPE.
PCIE_LAM Solution for Ego4D Looking At Me Challenge
This report presents our team's 'PCIE_LAM' solution for the Ego4D Looking At Me Challenge at CVPR2024.
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
While the impressive performance of modern neural networks is often attributed to their capacity to efficiently extract task-relevant features from data, the mechanisms underlying this rich feature learning regime remain elusive, with much of our theoretical understanding stemming from the opposing lazy regime.
Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
Then, by a theoretical study of two-layer ReLU networks optimized by stochastic gradient descent (SGD) under a structured feature model, we identify a fundamental yet unexplored feature learning proclivity of neural networks, feature contamination: neural networks can learn uncorrelated features together with predictive features, resulting in generalization failure under distribution shifts.
Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks
There is growing interest in using deep learning models for BEV semantic segmentation.
Streaming Video Diffusion: Online Video Editing with Diffusion Models
We present a novel task called online video editing, which is designed to edit \textbf{streaming} frames while maintaining temporal consistency.
Networked Integrated Sensing and Communications for 6G Wireless Systems
Furthermore, we analyze the mean square error of the proposed distributed algorithm as a networked sensing performance metric and propose a beamforming design for the proposed network ISAC scheme to maximize the networked sensing accuracy and communication performance subject to a transmit power constraint.
Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models
We empirically show that CausalDiffAE learns a disentangled latent space and is capable of generating high-quality counterfactual images.
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty due to composite class labels in training data in the context of the belief theory called Subjective Logic (SL).
CST: Calibration Side-Tuning for Parameter and Memory Efficient Transfer Learning
Achieving a universally high accuracy in object detection is quite challenging, and the mainstream focus in the industry currently lies on detecting specific classes of objects.
Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints.
Preserving Silent Features for Domain Generalization
In light of this, we propose a simple yet effective method termed STEP (Silent Feature Preservation) to improve the generalization performance of the self-supervised contrastive learning pre-trained model by alleviating the suppression of silent features during the supervised fine-tuning process.
FedSODA: Federated Cross-assessment and Dynamic Aggregation for Histopathology Segmentation
Federated learning (FL) for histopathology image segmentation involving multiple medical sites plays a crucial role in advancing the field of accurate disease diagnosis and treatment.
DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems.
Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shifts
We focus on confounding by provenance, a form of distribution shift that emerges in the context of multi-institutional datasets when there are differences in source-specific language use and class distributions.
Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting
We achieved 1st place in Detection, Tracking, and Forecasting on the E2E Forecasting track in Argoverse Challenges at CVPR 2023 WAD.
Technical Report for Argoverse Challenges on 4D Occupancy Forecasting
This report presents our Le3DE2E_Occ solution for 4D Occupancy Forecasting in Argoverse Challenges at CVPR 2023 Workshop on Autonomous Driving (WAD).
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV).
Ranked #1 on
Semantic Segmentation
on LaRS
Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously
The endeavor to preserve the generalization of a fair and invariant classifier across domains, especially in the presence of distribution shifts, becomes a significant and intricate challenge in machine learning.
Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
Sequential labeling is a task predicting labels for each token in a sequence, such as Named Entity Recognition (NER).
Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization
A large number of literature relies on uncertainty quantification to evaluate the reliability of a learning model, which is particularly important for applications of out-of-distribution (OOD) detection and misclassification detection.
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation.
Efficient Human-AI Coordination via Preparatory Language-based Convention
Developing intelligent agents capable of seamless coordination with humans is a critical step towards achieving artificial general intelligence.
Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models
Sixty proposed various strategies for mitigating biases, especially targeting implicit and selection biases.
Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction.
From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
Deep generative models have shown tremendous capability in data density estimation and data generation from finite samples.
Active Learning on Neural Networks through Interactive Generation of Digit Patterns and Visual Representation
In this paper, to improve users' learning and understanding of NNs, an interactive learning system is designed to create digit patterns and recognize them in real time.
Adapting Vision Foundation Models for Plant Phenotyping
The experimental results show that a foundation model can be efficiently adapted to multiple plant phenotyping tasks, yielding similar performance as the state-of-the-art (SoTA) models specifically designed or trained for each task.
Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective
In this study, we introduce a novel problem, semantic OOD detection across domains, which simultaneously addresses both distributional shifts.
Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER
Our BGA-MNER consists of \texttt{image2text} and \texttt{text2image} generation with respect to entity-salient content in two modalities.
ReIDTrack: Multi-Object Track and Segmentation Without Motion
Association techniques mainly depend on the combination of motion and appearance information.
Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
Below this threshold, the pretrained transformer cannot solve unseen regression tasks, instead behaving like a Bayesian estimator with the $\textit{non-diverse pretraining task distribution}$ as the prior.
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation Extraction
Multimodal Named Entity Recognition (MNER) and Multimodal Relation Extraction (MRE) necessitate the fundamental reasoning capacity for intricate linguistic and multimodal comprehension.
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving generalization.
Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
Further, to promote the disentanglement of causal factors, we propose a causal disentanglement prior learned from auxiliary labels and the latent causal structure.
Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features
These solutions employ Machine Learning (ML) models for behavioral modeling and critical security tasks such as malware and anomaly detection.
Towards Fair Disentangled Online Learning for Changing Environments
To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor.
Multiresolution Feature Guidance Based Transformer for Anomaly Detection
Under the tacit knowledge guidance of the AGN, the anomaly detection network named Trans utilizes Transformer to effectively establish a relationship between features with multiresolution, enhancing the ability of the Trans in fitting the normal data manifold.
InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition
To address these issues, this paper proposes InterFormer for interactive local and global features fusion to learn a better representation for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
The experimental results show that ASCD significantly improves the performance by leveraging both the acoustic and semantic information cooperatively.
SCTracker: Multi-object tracking with shape and confidence constraints
Detection-based tracking is one of the main methods of multi-object tracking.
Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity.
Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks.
Robust Multi-agent Communication via Multi-view Message Certification
Many multi-agent scenarios require message sharing among agents to promote coordination, hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment.
Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information
Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches.
Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
We also release the built offline benchmarks in this paper as a testbed for communication ability validation to facilitate further future research.
Uncertainty-guided Learning for Improving Image Manipulation Detection
Image manipulation detection (IMD) is of vital importance as faking images and spreading misinformation can be malicious and harm our daily life.
PPO-UE: Proximal Policy Optimization via Uncertainty-Aware Exploration
Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach.
Neural network quantum state with proximal optimization: a ground-state searching scheme based on variational Monte Carlo
Neural network quantum states (NQS), incorporating with variational Monte Carlo (VMC) method, are shown to be a promising way to investigate quantum many-body physics.
Block-Structured Optimization for Subgraph Detection in Interdependent Networks
We propose a generalized framework for block-structured nonconvex optimization, which can be applied to structured subgraph detection in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others.
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
Third, we show how the flatness of the error landscape at the end of training determines a limit on the fraction of weights that can be pruned at each iteration of IMP.
Framing Algorithmic Recourse for Anomaly Detection
We present an approach -- Context preserving Algorithmic Recourse for Anomalies in Tabular data (CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model.
Calibrated Nonparametric Scan Statistics for Anomalous Pattern Detection in Graphs
We propose a new approach, the calibrated nonparametric scan statistic (CNSS), for more accurate detection of anomalous patterns in large-scale, real-world graphs.
A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning
We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty.
Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision.
S4OD: Semi-Supervised learning for Single-Stage Object Detection
In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity.
Lane detection with Position Embedding
Recently, lane detection has made great progress in autonomous driving.
Ranked #2 on
Lane Detection
on TuSimple
Interacting Attention Graph for Single Image Two-Hand Reconstruction
To solve occlusion and interaction challenges of two-hand reconstruction, we introduce two novel attention based modules in each upsampling step of the original GCN.
Ranked #4 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
3D Interacting Hand Pose Estimation
Vocal Bursts Valence Prediction
Multi-Agent Policy Transfer via Task Relationship Modeling
We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks.
Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
During the forward pass of Deep Neural Networks (DNNs), inputs gradually transformed from low-level features to high-level conceptual labels.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
SEED: Sound Event Early Detection via Evidential Uncertainty
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes.
PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information
Meta learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks.
Transfering Hierarchical Structure with Dual Meta Imitation Learning
Hierarchical Imitation Learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations.
Learning Invariable Semantical Representation from Language for Extensible Policy Generalization
Recently, incorporating natural language instructions into reinforcement learning (RL) to learn semantically meaningful representations and foster generalization has caught many concerns.
Prototypical Model with Novel Information-theoretic Loss Function for Generalized Zero Shot Learning
Then We propose three information-theoretic loss functions for deterministic GZSL model: a mutual information loss to bridge seen data and target classes; an uncertainty-aware entropy constraint loss to prevent overfitting when using seen data to learn the embedding of target classes; a semantic preserving cross entropy loss to preserve the semantic relation when mapping the semantic representations to the common space.
Adjacency constraint for efficient hierarchical reinforcement learning
Searching in a large goal space poses difficulty for both high-level subgoal generation and low-level policy learning.
Transferring Hierarchical Structure with Dual Meta Imitation Learning
Hierarchical Imitation learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations.
Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification
Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i. e. the relations between local features, while ignoring the heterogeneous correlation of local features in different modalities.
Memory Regulation and Alignment toward Generalizer RGB-Infrared Person
The domain shift, coming from unneglectable modality gap and non-overlapped identity classes between training and test sets, is a major issue of RGB-Infrared person re-identification.
Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition
To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages.
Subjective Learning for Open-Ended Data
In this paper, we present a novel supervised learning framework of learning from open-ended data, which is modeled as data implicitly sampled from multiple domains with the data in each domain obeying a domain-specific target function.
Fairness-Aware Online Meta-learning
To overcome such issues and bridge the gap, in this paper for the first time we proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention.
Network-wide link travel time and station waiting time estimation using automatic fare collection data: A computational graph approach
This paper focuses on an essential and hard problem to estimate the network-wide link travel time and station waiting time using the automatic fare collection (AFC) data in the URT system, which is beneficial to better understand the system-wide real-time operation state.
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Deep learning's performance has been extensively recognized recently.
CRIL: Continual Robot Imitation Learning via Generative and Prediction Model
Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations.
RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
In this work, we propose RETRIEVE, a coreset selection framework for efficient and robust semi-supervised learning.
Local Aggressive Adversarial Attacks on 3D Point Cloud
However, the perturbations of global point are not effective for misleading the victim model.
FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting
To the best of our knowledge, this is the first network architecture with flow and deformation separation to model the evolution of radar echoes for precipitation nowcasting.
Success-Rate Targeted Reinforcement Learning by Disorientation Penalty
Unfortunately, applying traditional Bellman updates to value function learning can be problematic for learning undiscounted return, and thus not suitable for optimizing success rate.
Multidimensional Uncertainty-Aware Evidential Neural Networks
By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem.
Generative Adversarial Network
Multi-class Classification
+3
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data.
A Nested Bi-level Optimization Framework for Robust Few Shot Learning
Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal.
End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
Second, we propose to predict the quadrilateral bounding box in the local region by regressing the four corners of the license plate to robustly detect oblique license plates.
Uncertainty Aware Semi-Supervised Learning on Graph Data
To clarify the reasons behind the results, we provided the theoretical proof that explains the relationships between different types of uncertainties considered in this work.
How Out-of-Distribution Data Hurts Semi-Supervised Learning
This work addresses the following question: How do out-of-distribution (OOD) data adversely affect semi-supervised learning algorithms?
AI Centered on Scene Fitting and Dynamic Cognitive Network
This paper briefly analyzes the advantages and problems of AI mainstream technology and puts forward: To achieve stronger Artificial Intelligence, the end-to-end function calculation must be changed and adopt the technology system centered on scene fitting.
A Primal-Dual Subgradient Approachfor Fair Meta Learning
In this work, we propose a Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks.
Unfairness Discovery and Prevention For Few-Shot Regression
In this work, we first discover discrimination from data using a causal Bayesian knowledge graph which not only demonstrates the dependency of the protected variable on target but also indicates causal effects between all variables.
Rank-Based Multi-task Learning for Fair Regression
In this work, we develop a novel fairness learning approach for multi-task regression models based on a biased training dataset, using a popular rank-based non-parametric independence test, i. e., Mann Whitney U statistic, for measuring the dependency between target variable and protected variables.
Fair Meta-Learning For Few-Shot Classification
Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems.
Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method
The proposed model contributes to the development of short-term OD flow prediction, and it also lays the foundations of real-time URT operation and management.
SiENet: Siamese Expansion Network for Image Extrapolation
In this paper, a novel two-stage siamese adversarial model for image extrapolation, named Siamese Expansion Network (SiENet) is proposed.
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency constraint.
Brain-inspired global-local learning incorporated with neuromorphic computing
We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.
Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing.
Multi-Graph Convolutional Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit
Short-term passenger flow forecasting is a crucial task in the operation of urban rail transit.
Physics and Society
Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit
Finally, ResLSTM is applied to the Beijing subway using three time granularities (10, 15, and 30 min) to conduct short-term passenger flow forecasting.
Few-Features Attack to Fool Machine Learning Models through Mask-Based GAN
In comparison with the previous non-learning adversarial example attack approaches, the GAN-based adversarial attack example approach can generate the adversarial samples quickly using the GAN architecture every time facing a new sample after training, but meanwhile needs to perturb the attack samples in great quantities, which results in the unpractical application in reality.
Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
However, an ENN is trained as a black box without explicitly considering different types of inherent data uncertainty, such as vacuity (uncertainty due to a lack of evidence) or dissonance (uncertainty due to conflicting evidence).
Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions.
Uncertainty-Aware Prediction for Graph Neural Networks
In this work, we propose a Bayesian deep learning framework reflecting various types of uncertainties for classification predictions by leveraging the powerful modeling and learning capabilities of GNNs.
Evidence-Aware Entropy Decomposition For Active Deep Learning
We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data.
Subjective Reinforcement Learning for Open Complex Environments
In this paper, Subjective Reinforcement Learning Framework is proposed to state the problem from a broader and systematic view, and subjective policy is proposed to represent existing related algorithms in general.
Solving single-objective tasks by preference multi-objective reinforcement learning
We analyzed the feasibility of our algorithm in theory, and further proved in experiments its better performance compared to those that design the reward function by experts.
Multi-Objective Reinforcement Learning
reinforcement-learning
+1
Subjectivity Learning Theory towards Artificial General Intelligence
The construction of artificial general intelligence (AGI) was a long-term goal of AI research aiming to deal with the complex data in the real world and make reasonable judgments in various cases like a human.
Dual Averaging Method for Online Graph-structured Sparsity
Online learning algorithms update models via one sample per iteration, thus efficient to process large-scale datasets and useful to detect malicious events for social benefits, such as disease outbreak and traffic congestion on the fly.
Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization
Stochastic optimization algorithms update models with cheap per-iteration costs sequentially, which makes them amenable for large-scale data analysis.
Convolution with even-sized kernels and symmetric padding
Compact convolutional neural networks gain efficiency mainly through depthwise convolutions, expanded channels and complex topologies, which contrarily aggravate the training process.
NeuroTreeNet: A New Method to Explore Horizontal Expansion Network
It is widely recognized that the deeper networks or networks with more feature maps have better performance.
Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks
When a deep CNN with many layers is used for the visual system, it is not easy to compare the structure components of CNNs with possible neuroscience underpinnings due to highly complex circuits from the retina to higher visual cortex.
Layerwise Recurrent Autoencoder for General Real-world Traffic Flow Forecasting
To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction.
Abstraction Learning
Specifically, we propose a partition structure that contains pre-allocated abstraction neurons; we formulate abstraction learning as a constrained optimization problem, which integrates abstraction properties; we develop a network evolution algorithm to solve this problem.
Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator
RatioanlNet is proposed to integrate rational function and neural networks.
Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding
As the issue of freshwater shortage is increasing daily, it is critical to take effective measures for water conservation.
A Deep Learning Approach for Privacy Preservation in Assisted Living
In the era of Internet of Things (IoT) technologies the potential for privacy invasion is becoming a major concern especially in regards to healthcare data and Ambient Assisted Living (AAL) environments.
Training and Inference with Integers in Deep Neural Networks
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics.
Revealing structure components of the retina by deep learning networks
By training CNNs with white noise images to predicate neural responses, we found that convolutional filters learned in the end are resembling to biological components of the retinal circuit.
A Generic Framework for Interesting Subspace Cluster Detection in Multi-attributed Networks
As a case study, we specialize SG-Pursuit to optimize a number of well-known score functions for two typical tasks, including detection of coherent dense and anomalous connected subspace clusters in real-world networks.
Experimental comparison of single-pixel imaging algorithms
Various algorithms have been proposed for SPI reconstruction, including the linear correlation methods, the alternating projection method (AP), and the compressive sensing based methods.
SAFETY: Secure gwAs in Federated Environment Through a hYbrid solution with Intel SGX and Homomorphic Encryption
In this article, we present SAFETY, a hybrid framework, which can securely perform GWAS on federated genomic datasets using homomorphic encryption and recently introduced secure hardware component of Intel Software Guard Extensions (Intel SGX) to ensure high efficiency and privacy at the same time.
Cryptography and Security
Technical Report: A Generalized Matching Pursuit Approach for Graph-Structured Sparsity
Sparsity-constrained optimization is an important and challenging problem that has wide applicability in data mining, machine learning, and statistics.
Technical Report: Graph-Structured Sparse Optimization for Connected Subgraph Detection
Structured sparse optimization is an important and challenging problem for analyzing high-dimensional data in a variety of applications such as bioinformatics, medical imaging, social networks, and astronomy.
CaMKII activation supports reward-based neural network optimization through Hamiltonian sampling
Our theoretical analysis shows that stochastic search could in principle even attain optimal network configurations by emulating one of the most well-known nonlinear optimization methods, simulated annealing.