Search Results for author:
Found 89 papers, 28 papers with code
How memory biases affect information transmission: A rational analysis of serial reproduction
Many human interactions involve pieces of information being passed from one person to another, raising the question of how this process of information transmission is affected by the capacities of the agents involved.
Intrusion Detection using Continuous Time Bayesian Networks
For HIDS, we develop a novel learning method to deal with the finite resolution of system log file time stamps, without losing the benefits of our continuous time model.
Deep Boosting: Layered Feature Mining for General Image Classification
Constructing effective representations is a critical but challenging problem in multimedia understanding.
Image segmentation based on the hybrid total variation model and the K-means clustering strategy
The performance of image segmentation highly relies on the original inputting image.
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).
The Function Transformation Omics - Funomics
Function transformation, such as f(x, y) and f(x, y, z), can transform two, three, or multiple input/observation variables (in biology, it generally refers to the observed/measured value of biomarkers, biological characteristics, or other indicators) into a new output variable (new characteristics or indicators).
Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition
Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling.
Point-Based Multi-View Stereo Network
More specifically, our method predicts the depth in a coarse-to-fine manner.
S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
Grasping is among the most fundamental and long-lasting problems in robotics study.
Pose-Assisted Multi-Camera Collaboration for Active Object Tracking
In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images.
MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive.
Recipes for building an open-domain chatbot
Building open-domain chatbots is a challenging area for machine learning research.
Angular Triplet Loss-based Camera Network for ReID
Many complex network structures are proposed recently and many of them concentrate on multi-branch features to achieve high performance.
Optimization-driven Hierarchical Learning Framework for Wireless Powered Backscatter-aided Relay Communications
In this paper, we employ multiple wireless-powered relays to assist information transmission from a multi-antenna access point to a single-antenna receiver.
Integrated Communication and Localization in mmWave Systems
As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.
Recipes for Safety in Open-domain Chatbots
Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases.
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
Maximum target coverage by adjusting the orientation of distributed sensors is an important problem in directional sensor networks (DSNs).
AFINets: Attentive Feature Integration Networks for Image Classification
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks, e. g., image classification.
Learning Contextual Perturbation Budgets for Training Robust Neural Networks
We also demonstrate that the perturbation budget generator can produce semantically-meaningful budgets, which implies that the generator can capture contextual information and the sensitivity of different features in a given image.
RegNet: Self-Regulated Network for Image Classification
The ResNet and its variants have achieved remarkable successes in various computer vision tasks.
Ranked #3 on
Medical Image Classification
on NCT-CRC-HE-100K
Non-Ohmic negative longitudinal magnetoresistance in two-dimensional electron gas
Negative longitudinal magnetoresistance (NLMR) has been reported in a variety of materials and has attracted extensive attention as an electrotransport hallmark of topological Weyl semimetals.
Materials Science Mesoscale and Nanoscale Physics
MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance
Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently.
Optically reconfigurable quantum spin-valley Hall effect of light in coupled nonlinear ring resonator lattice
In optics, various photonic topological circuits have been developed, which were based on classical emulation of either quantum spin Hall effect or quantum valley Hall effect.
Optics
Explainability-based Backdoor Attacks Against Graph Neural Networks
Backdoor attacks represent a serious threat to neural network models.
Noise Attention based Spectrum Anomaly Detection Method for Unauthorized Bands
In this paper, a noise attention method is proposed for unsupervised spectrum anomaly detection in unauthorized bands.
AFINet: Attentive Feature Integration Networks for Image Classification
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification.
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.
Bot-Adversarial Dialogue for Safe Conversational Agents
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior.
On Anytime Learning at Macroscale
Practitioners have then to decide how to allocate their computational budget in order to obtain the best performance at any point in time.
FedCM: Federated Learning with Client-level Momentum
Federated Learning is a distributed machine learning approach which enables model training without data sharing.
Beyond Goldfish Memory: Long-Term Open-Domain Conversation
Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context.
A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image
The large-scale OCTA dataset is available at https://doi. org/10. 5281/zenodo. 5111975, https://doi. org/10. 5281/zenodo. 5111972.
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Modularized Interaction Network for Named Entity Recognition
Although the existing Named Entity Recognition (NER) models have achieved promising performance, they suffer from certain drawbacks.
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
The asymmetric bilateral encoder has a transformer path and a lightweight CNN path, where the two paths communicate at each encoder stage to learn complementary global contexts and local spatial details, respectively.
Boosting Graph Search with Attention Network for Solving the General Orienteering Problem
We propose a novel combination of a variant beam search algorithm and a learned heuristic for solving the general orienteering problem.
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Current open-domain conversational models can easily be made to talk in inadequate ways.
ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind
With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation.
Watermarking Graph Neural Networks based on Backdoor Attacks
The experiments show that our framework can verify the ownership of GNN models with a very high probability (up to $99\%$) for both tasks.
Exploring Category-correlated Feature for Few-shot Image Classification
To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge.
S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation
Emotion recognition in conversation (ERC) has attracted much attention in recent years for its necessity in widespread applications.
Ranked #1 on
Emotion Recognition in Conversation
on DailyDialog
More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
To further explore the properties of two backdoor attacks in Federated GNNs, we evaluate the attack performance for a different number of clients, trigger sizes, poisoning intensities, and trigger densities.
Semantically Proportional Patchmix for Few-Shot Learning
Few-shot learning aims to classify unseen classes with only a limited number of labeled data.
Freeform Body Motion Generation from Speech
Motivated by studies in linguistics, we decompose the co-speech motion into two complementary parts: pose modes and rhythmic dynamics.
Channel Importance Matters in Few-Shot Image Classification
When facing novel few-shot tasks in the test-time datasets, this transformation can greatly improve the generalization ability of learned image representations, while being agnostic to the choice of training algorithms and datasets.
Label-Only Membership Inference Attack against Node-Level Graph Neural Networks
Even in those scenarios, our label-only MIA achieves a better attack performance in most cases.
SSformer: A Lightweight Transformer for Semantic Segmentation
It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks.
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks.
Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
The promise of interaction between intelligent conversational agents and humans is that models can learn from such feedback in order to improve.
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
We then study various algorithms for improving from such feedback, including standard supervised learning, rejection sampling, model-guiding and reward-based learning, in order to make recommendations on which type of feedback and algorithms work best.
A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction
Our framework can model complicated relations between emotions and causes while avoiding generating the pairing matrix (the leading cause of the label sparsity problem).
Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose.
When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels
Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves.
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task.
The CRINGE Loss: Learning what language not to model
Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples.
UperFormer: A Multi-scale Transformer-based Decoder for Semantic Segmentation
On the more challenging ADE20K dataset, our best model yields a single-scale mIoU of 50. 18, and a multi-scale mIoU of 51. 8, which is on-par with the current state-of-art model, while we drastically cut the number of FLOPs by 53. 5%.
TriPINet: Tripartite Progressive Integration Network for Image Manipulation Localization
In this paper, we propose a tripartite progressive integration network (TriPINet) for end-to-end image manipulation localization.
On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis
Bilevel optimization reveals the inner structure of otherwise oblique optimization problems, such as hyperparameter tuning, neural architecture search, and meta-learning.
Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
We consider the optimization problem of the form $\min_{x \in \mathbb{R}^d} f(x) \triangleq \mathbb{E}_{\xi} [F(x; \xi)]$, where the component $F(x;\xi)$ is $L$-mean-squared Lipschitz but possibly nonconvex and nonsmooth.
A Closer Look at Few-shot Classification Again
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples.
SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model.
Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking
In this paper, we propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states and migrate the gap of utilization between training and testing.
Dynamic Graph Neural Network with Adaptive Edge Attributes for Air Quality Predictions
Previous GCNs-based methods usually require providing spatial correlation graph structure of observation sites in advance.
Rethinking the Trigger-injecting Position in Graph Backdoor Attack
There is no work analyzing and explaining the backdoor attack performance when injecting triggers into the most important or least important area in the sample, which we refer to as trigger-injecting strategies MIAS and LIAS, respectively.
Continual Dialogue State Tracking via Example-Guided Question Answering
Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services.
Quantifying the Variability Collapse of Neural Networks
The recently discovered Neural Collapse (NC) phenomenon provides a new perspective of understanding such last layer geometry of neural networks.
Improving Open Language Models by Learning from Organic Interactions
We present BlenderBot 3x, an update on the conversational model BlenderBot 3, which is now trained using organic conversation and feedback data from participating users of the system in order to improve both its skills and safety.
Searching for the Fakes: Efficient Neural Architecture Search for General Face Forgery Detection
The cross-dataset search is also considered to develop more general architectures.
HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection
Specifically, we design a high-order spatial fusion (HOSF) module and a high-order channel fusion (HOCF) module to fuse features of the first two and the last two stages, respectively.
Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
Many cognitive approaches to well-being, such as recognizing and reframing unhelpful thoughts, have received considerable empirical support over the past decades, yet still lack truly widespread adoption in self-help format.
A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images
Skin diseases are among the most prevalent health issues, and accurate computer-aided diagnosis methods are of importance for both dermatologists and patients.
Label Inference Attacks against Node-level Vertical Federated GNNs
In this work, we are the first (to the best of our knowledge) to investigate label inference attacks on VFL using a zero-background knowledge strategy.
TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touches
By approximating and optimizing the utility function, we can optimize the probing locations given a fixed touching budget to better improve the network's performance on real objects.
Chain-of-Verification Reduces Hallucination in Large Language Models
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models.
A Quantum States Preparation Method Based on Difference-Driven Reinforcement Learning
To solve the above problems, a difference-driven reinforcement learning (RL) algorithm for quantum state preparation of two-qubit system is proposed by improving the reward function and action selection strategy.
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data
Our findings highlight the urgency of addressing such vulnerabilities and provide insights into potential countermeasures for securing DNN models against backdoors in tabular data.
GMISeg: General Medical Image Segmentation without Re-Training
Therefore, we proposed a general method that can solve unknown medical image segmentation tasks without requiring additional training.
CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs
CAD programs are a popular way to compactly encode shapes as a sequence of operations that are easy to parametrically modify.
MS-Twins: Multi-Scale Deep Self-Attention Networks for Medical Image Segmentation
Even compared with nnUNet, the best entirely convoluted medical image segmentation network, the performance of MS-Twins on Synapse and ACDC still has a bit advantage.
Some things are more CRINGE than others: Preference Optimization with the Pairwise Cringe Loss
Practitioners commonly align large language models using pairwise preferences, i. e., given labels of the type response A is preferred to response B for a given input.
Self-Rewarding Language Models
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal.
ParaTransCNN: Parallelized TransCNN Encoder for Medical Image Segmentation
The convolutional neural network-based methods have become more and more popular for medical image segmentation due to their outstanding performance.
Ranked #8 on
Medical Image Segmentation
on Synapse multi-organ CT
(using extra training data)
Key Patch Proposer: Key Patches Contain Rich Information
In this paper, we introduce a novel algorithm named Key Patch Proposer (KPP) designed to select key patches in an image without additional training.
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition
First, we leverage parameter-efficient prompt tuning to drive the inputted arguments to match the pre-trained space and realize the approximation with few parameters.
Device Fault Prediction Model based on LSTM and Random Forest
For purpose of complete the above tasks, this paper investigates the use of Long Short-Term Memory (LSTM) algorithms for quality prediction in material equipment based on key inspection parameters.
Sampling Model for Grid Material Inspection Based on Analytic Hierarchy Process with Absolute Measurement
For purpose of complete the above tasks, this paper investigates the use of Long Short-Term Memory (LSTM) algorithms for quality prediction in material equipment based on key inspection parameters.
Correlation analysis technique of key parameters for transformer material inspection based on FP-tree and knowledge graph
Given the above problems, this paper aims to mine the relationship between the unqualified distribution transformer inspection items by using the association rule algorithm based on the distribution transformer inspection data collected from 2017 to 2021 and sorting out the key inspection items.
HyperCLOVA X Technical Report
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding.
ZHIXIAOBAO at SemEval-2022 Task 10: Apporoaching Structured Sentiment with Graph Parsing
This paper presents our submission to task 10, Structured Sentiment Analysis of the SemEval 2022 competition.
