Search Results for author:
Found 164 papers, 69 papers with code
C^3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Masked Autoencoders are Efficient Class Incremental Learners
Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL.
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception.
LiDAR Meta Depth Completion
While using a single model, our method yields significantly better results than a non-adaptive baseline trained on different LiDAR patterns.
Prompting Large Language Models with Speech Recognition Abilities
Furthermore, we perform ablation studies to investigate whether the LLM can be completely frozen during training to maintain its original capabilities, scaling up the audio encoder, and increasing the audio encoder striding to generate fewer embeddings.
Abstractive Text Summarization
Automatic Speech Recognition
+3
PAPR: Proximity Attention Point Rendering
PAPR effectively learns point cloud positions to represent the correct scene geometry, even when the initialization drastically differs from the target geometry.
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning
Specifically, with the help of CBF method, we learn the inherent and external uncertainties by a unified adaptive Bayesian linear regression (ABLR) model, which consists of a forward neural network (NN) and a Bayesian output layer.
MEMD-ABSA: A Multi-Element Multi-Domain Dataset for Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis is a long-standing research interest in the field of opinion mining, and in recent years, researchers have gradually shifted their focus from simple ABSA subtasks to end-to-end multi-element ABSA tasks.
A Survey on Multimodal Large Language Models
Multimodal Large Language Model (MLLM) recently has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks.
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image.
Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem.
Multi-modal Queried Object Detection in the Wild
To address the learning inertia problem brought by the frozen detector, a vision conditioned masked language prediction strategy is proposed.
READ: Recurrent Adaptation of Large Transformers
However, fine-tuning all pre-trained model parameters becomes impractical as the model size and number of tasks increase.
Integrating Multiple Sources Knowledge for Class Asymmetry Domain Adaptation Segmentation of Remote Sensing Images
Firstly, a multi-branch segmentation network is built to learn an expert for each source RSI.
Compressing neural network by tensor network with exponentially fewer variational parameters
Neural network (NN) designed for challenging machine learning tasks is in general a highly nonlinear mapping that contains massive variational parameters.
Reactive Perturbation Defocusing for Textual Adversarial Defense
Existing methods attempt to reconstruct the adversarial examples.
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
We propose a factorization that models independent part style and part configuration distributions and presents a novel cross-diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization.
SketchXAI: A First Look at Explainability for Human Sketches
Following this, we design a simple explainability-friendly sketch encoder that accommodates the intrinsic properties of strokes: shape, location, and order.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Diffusion models with location-scale noise
Diffusion Models (DMs) are powerful generative models that add Gaussian noise to the data and learn to remove it.
HybridFusion: LiDAR and Vision Cross-Source Point Cloud Fusion
First, the point cloud is divided into small patches, and a matching patch set is selected based on global descriptors and spatial distribution, which constitutes the coarse matching process.
RFAConv: Innovating Spatial Attention and Standard Convolutional Operation
In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that the spatial attention mechanism essentially solves the problem of convolutional kernel parameter sharing.
SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger
During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks.
SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
To address this issue, we introduce SCADE, a novel technique that improves NeRF reconstruction quality on sparse, unconstrained input views for in-the-wild indoor scenes.
CLIP4MC: An RL-Friendly Vision-Language Model for Minecraft
One of the essential missions in the AI research community is to build an autonomous embodied agent that can attain high-level performance across a wide spectrum of tasks.
Practical Cross-System Shilling Attacks with Limited Access to Data
With the idea of Cross-system Attack, we design a Practical Cross-system Shilling Attack (PC-Attack) framework that requires little information about the victim RS model and the target RS data for conducting attacks.
Quality Indicators for Preference-based Evolutionary Multi-objective Optimization Using a Reference Point: A Review and Analysis
Some quality indicators have been proposed for benchmarking preference-based evolutionary multi-objective optimization algorithms using a reference point.
Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation
However, existing methods often struggle to simultaneously minimize the number of modified pixels and the size of the modifications, often requiring a large number of queries and assuming unrestricted access to the targeted DNN.
Photo Pre-Training, but for Sketch
This lack of sketch data has imposed on the community a few "peculiar" design choices -- the most representative of them all is perhaps the coerced utilisation of photo-based pre-training (i. e., no sketch), for many core tasks that otherwise dictates specific sketch understanding.
Fewer is More: Efficient Object Detection in Large Aerial Images
Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not.
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Robust Saliency Guidance for Data-free Class Incremental Learning
Data-Free Class Incremental Learning (DFCIL) aims to sequentially learn tasks with access only to data from the current one.
Improving Fast-slow Encoder based Transducer with Streaming Deliberation
Experiments on Librispeech and in-house data show relative WER reductions (WERRs) from 3% to 5% with a slight increase in model size and negligible extra token emission latency compared with fast-slow encoder based transducer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis
A persistent challenge in conditional image synthesis has been to generate diverse output images from the same input image despite only one output image being observed per input image.
Immersive Neural Graphics Primitives
In this paper, we present and evaluate a NeRF-based framework that is capable of rendering scenes in immersive VR allowing users to freely move their heads to explore complex real-world scenes.
A Data-Driven Evolutionary Transfer Optimization for Expensive Problems in Dynamic Environments
Many real-world problems are usually computationally costly and the objective functions evolve over time.
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data.
Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders
We utilize the micro-macro objective to improve graph generation with a GraphVAE, a well-established model based on graph-level latent variables, that provides fast training and generation time for medium-sized graphs.
Augmentor or Filter? Reconsider the Role of Pre-trained Language Model in Text Classification Augmentation
Our study shows that even employing pre-trained language models, existing text augmentation methods generate numerous low-quality instances and lead to the feature space shift problem in augmentation instances.
Long-Tailed Class Incremental Learning
However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world.
Defend Data Poisoning Attacks on Voice Authentication
With the advances in deep learning, speaker verification has achieved very high accuracy and is gaining popularity as a type of biometric authentication option in many scenes of our daily life, especially the growing market of web services.
LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal
Finally, the LSA modules are further developed to fully use the prior information in non-shadow regions to cleanse the shadow regions.
PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis
The advancement of aspect-based sentiment analysis (ABSA) has urged the lack of a user-friendly framework that can largely lower the difficulty of reproducing state-of-the-art ABSA performance, especially for beginners.
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary.
Ranked #6 on
Open Vocabulary Object Detection
on LVIS v1.0
Learning Best Combination for Efficient N:M Sparsity
In this paper, we show that the N:M learning can be naturally characterized as a combinatorial problem which searches for the best combination candidate within a finite collection.
Efficient Decoder-free Object Detection with Transformers
A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with the price of bringing considerable computation burden for inference.
Evolutionary Multi-Task Injection Testing on Web Application Firewalls
In this paper, we propose DaNuoYi, an automatic injection testing tool that simultaneously generates test inputs for multiple types of injection attacks on a WAF.
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
U-Nets have achieved tremendous success in medical image segmentation.
Do We Really Need to Use Constraint Violation in Constrained Evolutionary Multi-Objective Optimization?
Constraint violation has been a building block to design evolutionary multi-objective optimization algorithms for solving constrained multi-objective optimization problems.
Data-Driven Evolutionary Multi-Objective Optimization Based on Multiple-Gradient Descent for Disconnected Pareto Fronts
Data-driven evolutionary multi-objective optimization (EMO) has been recognized as an effective approach for multi-objective optimization problems with expensive objective functions.
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining
Large-scale vision-language pre-training has achieved promising results on downstream tasks.
Interactive Evolutionary Multi-Objective Optimization via Learning-to-Rank
Bearing this in mind, this paper develops a framework for designing preference-based EMO algorithms to find SOI in an interactive manner.
C3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Streaming parallel transducer beam search with fast-slow cascaded encoders
Streaming ASR with strict latency constraints is required in many speech recognition applications.
Training-free Transformer Architecture Search
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.
ARM: Any-Time Super-Resolution Method
To that effect, we construct an Edge-to-PSNR lookup table that maps the edge score of an image patch to the PSNR performance for each subnet, together with a set of computation costs for the subnets.
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image.
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
However, these methods suffer from severe performance degradation when quantizing the SR models to ultra-low precision (e. g., 2-bit and 3-bit) with the low-cost layer-wise quantizer.
Automated Few-Shot Time Series Forecasting based on Bi-level Programming
One of the critical challenges of time series renewable energy forecasting is the lack of historical data to train an adequate predictive model.
Art-Attack: Black-Box Adversarial Attack via Evolutionary Art
To evaluate the effectiveness of our proposed method, we attack three state-of-the-art image classification models trained on the CIFAR-10 dataset in a targeted manner.
Variational Model Inversion Attacks
In this work, we provide a probabilistic interpretation of model inversion attacks, and formulate a variational objective that accounts for both diversity and accuracy.
End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization
In this work, we take a new route to learn to optimize the LiDAR beam configuration for a given application.
LONViZ: Unboxing the black-box of Configurable Software Systems from a Complex Networks Perspective
Due to the black-box nature, it is difficult, if not impossible, to analyze and understand its behavior, such as the interaction between combinations of configuration options with regard to the performance, in particular, which is of great importance to advance the controllability of the underlying software system.
RMNet: Equivalently Removing Residual Connection from Networks
In this paper, we aim to remedy this problem and propose to remove the residual connection in a vanilla ResNet equivalently by a reserving and merging (RM) operation on ResBlock.
Improving Implicit Sentiment Learning via Local Sentiment Aggregation
Aspect-based sentiment classification (ABSC) has revealed the potential dependency of sentiment polarities among different aspects.
Aspect-Based Sentiment Analysis (ABSA)
Sentiment Classification
+1
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution.
Anchor-free Oriented Proposal Generator for Object Detection
Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them.
Generating Unobserved Alternatives with Tower Implicit Model (TIM)
We consider problems where multiple predictions can be considered correct, but only one of them is given as supervision.
Self-supervised Models are Good Teaching Assistants for Vision Transformers
These findings motivate us to introduce an self-supervised teaching assistant (SSTA) besides the commonly used supervised teacher to improve the performance of transformers.
A Two-Stage Framework to Generate Video Chapter
On top of this dataset, we propose a two-stage framework to perform chapter localization and chapter title generation.
Private Language Model Adaptation for Speech Recognition
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Gotta Go Fast with Score-Based Generative Models
Score-based (denoising diffusion) generative models have recently gained a lot of success in generating realistic and diverse data.
Regret Lower Bound and Optimal Algorithm for High-Dimensional Contextual Linear Bandit
This new lower bound unifies existing regret bound results that have different dependencies on T due to the use of different values of margin parameter $\alpha$ explicitly implied by their assumptions.
Batched Data-Driven Evolutionary Multi-Objective Optimization Based on Manifold Interpolation
Data-driven evolutionary optimization can be used to search for a set of non-dominated trade-off solutions, where the expensive objective functions are approximated as a surrogate model.
Fine-grained Data Distribution Alignment for Post-Training Quantization
While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images.
Decomposition Multi-Objective Evolutionary Optimization: From State-of-the-Art to Future Opportunities
Decomposition has been the mainstream approach in the classic mathematical programming for multi-objective optimization and multi-criterion decision-making.
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction
To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features.
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue.
Ranked #473 on
Image Classification
on ImageNet
Multimodal Shape Completion via IMLE
Shape completion is the problem of completing partial input shapes such as partial scans.
Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning
Our experiments demonstrate a significant improvement in the realism of the generated graph structures, typically by 1-2 orders of magnitude of graph structure metrics, compared to leading graph VAEand GAN models.
Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
Deep generative models such as GANs have driven impressive advances in conditional image synthesis in recent years.
Deep Medial Fields
Implicit representations of geometry, such as occupancy fields or signed distance fields (SDF), have recently re-gained popularity in encoding 3D solid shape in a functional form.
Gotta Go Fast When Generating Data with Score-Based Models
For high-resolution images, our method leads to significantly higher quality samples than all other methods tested.
Ranked #8 on
Image Generation
on CIFAR-10
(Inception score metric)
Unsupervised Discriminative Learning of Sounds for Audio Event Classification
Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet.
Towards an Online Empathetic Chatbot with Emotion Causes
Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #20 on
Instance Segmentation
on COCO test-dev
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher.
Pose Recognition with Cascade Transformers
Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches.
speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment
This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children.
Ranked #6 on
Phone-level pronunciation scoring
on speechocean762
On Evolving Attention Towards Domain Adaptation
However, considering that the configuration of attention, i. e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario.
Ranked #1 on
Unsupervised Domain Adaptation
on Duke to Market
Multi-Objective Reinforcement Learning based Multi-Microgrid System Optimisation Problem
The proposed model consists of three layers, smart grid layer, independent system operator (ISO) layer and power grid layer.
An Improved Two-Archive Evolutionary Algorithm for Constrained Multi-Objective Optimization
Constrained multi-objective optimization problems (CMOPs) are ubiquitous in real-world engineering optimization scenarios.
A Parallelizable Lattice Rescoring Strategy with Neural Language Models
This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Combinatorial Bandits under Strategic Manipulations
Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed.
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets
With these contributions, our method is able to learn from heterogeneous datasets and lift the requirement for having a large amount of HD HSI training samples.
An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
Pseudo-labeling (PL) and Data Augmentation-based Consistency Training (DACT) are two approaches widely used in Semi-Supervised Learning (SSL) methods.
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
