Search Results for author:
Found 63 papers, 18 papers with code
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.
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.
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.
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.
On Bilevel Optimization without Lower-level Strong Convexity
Theoretical properties of bilevel problems are well studied when the lower-level problem is strongly convex.
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.
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%.
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.
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.
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.
Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
To test our method in real scenarios and enable future studies on generalizable visual-tactile tracking, we collect a real visual-tactile in-hand object pose tracking dataset.
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).
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.
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 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.
SSformer: A Lightweight Transformer for Semantic Segmentation
It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks.
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.
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.
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.
Semantically Proportional Patchmix for Few-Shot Learning
Few-shot learning aims to classify unseen classes with only a limited number of labeled data.
When do Models Generalize? A Perspective from Data-Algorithm Compatibility
By considering the entire training trajectory and focusing on early-stopping iterates, compatibility exploits the data and the algorithm information and is therefore a more suitable notion for generalization.
More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
We find that both attacks are robust against the investigated defenses, necessitating the need to consider backdoor attacks in Federated GNNs as a novel threat that requires custom defenses.
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
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.
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.
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.
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
Current open-domain conversational models can easily be made to talk in inadequate ways.
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.
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.
Modularized Interaction Network for Named Entity Recognition
Although the existing Named Entity Recognition (NER) models have achieved promising performance, they suffer from certain drawbacks.
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers.
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.
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.
FedCM: Federated Learning with Client-level Momentum
Federated Learning is a distributed machine learning approach which enables model training without data sharing.
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.
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.
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.
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.
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.
Explainability-based Backdoor Attacks Against Graph Neural Networks
Backdoor attacks represent a serious threat to neural network models.
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
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.
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
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
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.
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 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).
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.
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.
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.
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.
Recipes for building an open-domain chatbot
Building open-domain chatbots is a challenging area for machine learning research.
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.
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.
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.
Point-Based Multi-View Stereo Network
More specifically, our method predicts the depth in a coarse-to-fine manner.
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.
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).
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).
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.
Deep Boosting: Layered Feature Mining for General Image Classification
Constructing effective representations is a critical but challenging problem in multimedia understanding.
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.
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.
