Search Results for author:
Found 81 papers, 36 papers with code
Generating Valid and Natural Adversarial Examples with Large Language Models
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks.
Zero-Shot Medical Information Retrieval via Knowledge Graph Embedding
In the era of the Internet of Things (IoT), the retrieval of relevant medical information has become essential for efficient clinical decision-making.
Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Model-enhanced Vector Index
We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.
Domain Adaptive Synapse Detection with Weak Point Annotations
In the second stage, we improve model generalizability on target data by regenerating square masks to get high-quality pseudo labels.
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions.
Dynamic Strategy Chain: Dynamic Zero-Shot CoT for Long Mental Health Support Generation
The combination of chain-of-thought (CoT) prompting and Large Language Models (LLMs) is employed and get the SOTA performance on various NLP tasks, especially on text generation tasks.
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations.
Likelihood-Based Text-to-Image Evaluation with Patch-Level Perceptual and Semantic Credit Assignment
In this paper, we propose to evaluate text-to-image generation performance by directly estimating the likelihood of the generated images using a pre-trained likelihood-based text-to-image generative model, i. e., a higher likelihood indicates better perceptual quality and better text-image alignment.
Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval
In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e. g., CLIP) by adapting them to the video domain.
Chinese Financial Text Emotion Mining: GCGTS -- A Character Relationship-based Approach for Simultaneous Aspect-Opinion Pair Extraction
This innovative structure reduces the excessive reliance on pre-trained language models and emphasizes the modeling of structure and local relationships, thereby improving the performance of the model on Chinese financial texts.
Path Integral Method for Barrier Option Pricing Under Vasicek Model
Path integral method in quantum theory provides a new thinking for time dependent option pricing.
End-to-End Out-of-distribution Detection with Self-supervised Sampling
Out-of-distribution (OOD) detection empowers the model trained on the closed set to identify unknown data in the open world.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Improving Tuning-Free Real Image Editing with Proximal Guidance
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
S4M: Generating Radiology Reports by A Single Model for Multiple Body Parts
In this paper, we seek to design a report generation model that is able to generate reasonable reports even given different images of various body parts.
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
We further provide algorithm-dependent generalization bounds for these two settings, where the generalization is characterized by the mutual information between the parameters and the data.
DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
Additionally, we propose a novel method for generating continuous video frames with the DDIM image decoder trained on individual frames, eliminating the need for modelling the joint distribution of consecutive frames directly.
IRGen: Generative Modeling for Image Retrieval
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored.
AutoMatch: A Large-scale Audio Beat Matching Benchmark for Boosting Deep Learning Assistant Video Editing
In this paper, we investigate a novel and practical problem, namely audio beat matching (ABM), which aims to recommend the proper transition time stamps based on the background music.
SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous Driving
However, there is a lack of underground parking scenario datasets with multiple sensors and well-labeled images that support both SLAM tasks and perception tasks, such as semantic segmentation and parking slot detection.
Path Integral Method for Pricing Proportional Step Double-Barrier Option with Time Dependent Parameters
Path integral method in quantum mechanics provides a new thinking for barrier option pricing.
GMConv: Modulating Effective Receptive Fields for Convolutional Kernels
Inspired by the property that ERFs typically exhibit a Gaussian distribution, we propose a Gaussian Mask convolutional kernel (GMConv) in this work.
SR-Forest: A Genetic Programming based Heterogeneous Ensemble Learning Method
Ensemble learning methods have been widely used in machine learning in recent years due to their high predictive performance.
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts.
Online Loss Function Learning
Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model.
StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding
The effectiveness of the proposed model for the zero-shot traditional Chinese font generation is also evaluated in this paper.
On Learning Fairness and Accuracy on Multiple Subgroups
In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors.
Pareto-aware Neural Architecture Generation for Diverse Computational Budgets
More critically, these independent search processes cannot share their learned knowledge (i. e., the distribution of good architectures) with each other and thus often result in limited search results.
Path Integral Method for Floating Barrier Option Pricing
Path integral method in quantum mechanics provides a new thinking for barrier option pricing.
Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning
In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them.
Learning Distinct and Representative Styles for Image Captioning
Our innovative idea is to explore the rich modes in the training caption corpus to learn a set of "mode embeddings", and further use them to control the mode of the generated captions for existing image captioning models.
Towards Lightweight Super-Resolution with Dual Regression Learning
Nevertheless, it is hard for existing model compression methods to accurately identify the redundant components due to the extremely large SR mapping space.
Optimization-Induced Graph Implicit Nonlinear Diffusion
Moreover, we show that the optimization-induced variants of our models can boost the performance and improve training stability and efficiency as well.
Formation Tracking for a Multi-Auv System Based on an Adaptive Sliding Mode Method in the Water Flow Environment
At last, a robust sliding mode controller with continuous model predictive control strategy for the multi-AUV system is developed to achieve leader-follower formation tracking under the presence of bounded flow disturbances, and simulations are implemented to confirm the effectiveness of the proposed method.
A Neural Corpus Indexer for Document Retrieval
To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query.
Fair Representation Learning through Implicit Path Alignment
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups.
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
The outcome of the competition was ranked leaderboards of algorithms in each track based on recall at a query throughput threshold.
Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity
We propose a simple yet effective proposal-free architecture for lidar panoptic segmentation.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs.
Ranked #13 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Path Integral Method for Proportional Step and Proportional Double-Barrier Step Option Pricing
Path integral method in quantum mechanics provides a new thinking for barrier option pricing.
PolarStream: Streaming Object Detection and Segmentation with Polar Pillars
Recent works recognized lidars as an inherently streaming data source and showed that the end-to-end latency of lidar perception models can be reduced significantly by operating on wedge-shaped point cloud sectors rather then the full point cloud.
V2C: Visual Voice Cloning
Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio.
Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers.
SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search
It stores the centroid points of the posting lists in the memory and the large posting lists in the disk.
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis
We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms.
PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars
Recent works recognized lidars as an inherently streaming data source and showed that the end-to-end latency of lidar perception models can be reduced significantly by operating on wedge-shaped point cloud sectors rather then the full point cloud.
Ranked #21 on
LIDAR Semantic Segmentation
on nuScenes
SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search
It stores the centroid points of the posting lists in the memory and the large posting lists in the disk.
Contrastive Neural Architecture Search with Neural Architecture Comparators
One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures.
Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets
To this end, we propose a Pareto-Frontier-aware Neural Architecture Generator (NAG) which takes an arbitrary budget as input and produces the Pareto optimal architecture for the target budget.
Towards Accurate and Compact Architectures via Neural Architecture Transformer
To address this issue, we propose a Neural Architecture Transformer++ (NAT++) method which further enlarges the set of candidate transitions to improve the performance of architecture optimization.
StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
However, these deep generative models may suffer from the mode collapse issue, which significantly degrades the diversity and quality of generated results.
Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization
We proposed a pair of cross-view transformers to transform the feature maps into the other view and introduce cross-view consistency loss on them.
Modular Graph Attention Network for Complex Visual Relational Reasoning
Moreover, to capture the complex logic in a query, we construct a relational graph to represent the visual objects and their relationships, and propose a multi-step reasoning method to progressively understand the complex logic.
Ranked #2 on
Referring Expression Comprehension
on CLEVR-Ref+
CoFF: Cooperative Spatial Feature Fusion for 3D Object Detection on Autonomous Vehicles
To reduce the amount of transmitted data, feature map based fusion is recently proposed as a practical solution to cooperative 3D object detection by autonomous vehicles.
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence.
GLOW : Global Weighted Self-Attention Network for Web Search
Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval.
DCANet: Learning Connected Attentions for Convolutional Neural Networks
With DCANet, all attention blocks in a CNN model are trained jointly, which improves the ability of attention learning.
Attention-guided Context Feature Pyramid Network for Object Detection
For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question.
Ranked #73 on
Object Detection
on COCO test-dev
A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
In this paper, we aim to review various adversarial attack and defense methods on chest X-rays.
Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
Extensive experiments with paired training data and unpaired real-world data demonstrate our superiority over existing methods.
Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN).
Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities.
Ranked #3 on
3D Object Detection
on KITTI Pedestrians Moderate
NAT: Neural Architecture Transformer for Accurate and Compact Architectures
To verify the effectiveness of the proposed strategies, we apply NAT on both hand-crafted architectures and NAS based architectures.
MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity
We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus.
F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds
Autonomous vehicles are heavily reliant upon their sensors to perfect the perception of surrounding environments, however, with the current state of technology, the data which a vehicle uses is confined to that from its own sensors.
Ranked #4 on
3D Object Detection
on OPV2V
FPCNet: Fast Pavement Crack Detection Network Based on Encoder-Decoder Architecture
Specifically, we first propose the Multi-Dilation (MD) module, which can synthesize the crack features of multiple context sizes via dilated convolution with multiple rates.
Semi-parametric Bayesian variable selection for gene-environment interactions
Existing Bayesian methods for G$\times$E interaction studies are challenged by the high-dimensional nature of the study and the complexity of environmental influences.
Methodology
Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds
A point cloud based 3D object detection method is proposed to work on a diversity of aligned point clouds.
Ranked #3 on
3D Object Detection
on OPV2V
Natural Language Inference with Monotonicity
This paper describes a working system which performs natural language inference using polarity-marked parse trees.
Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
To address this issue, we develop a novel GAN called Auto-Embedding Generative Adversarial Network (AEGAN), which simultaneously encodes the global structure features and captures the fine-grained details.
DUNet: A deformable network for retinal vessel segmentation
Results show that more detailed vessels are extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0. 9697/0. 9722/0. 9724 and AUC of 0. 9856/0. 9868/0. 9863 on DRIVE, STARE and CHASE_DB1 respectively.
Ranked #5 on
Retinal Vessel Segmentation
on STARE
Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning
The lack of labeled data is one of the main challenges when building a task-oriented dialogue system.
Semantic Segmentation for Urban Planning Maps based on U-Net
The results indicate the proposed method can serve as a viable tool for urban planning map semantic segmentation task with high accuracy and efficiency.
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance.
Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
In this paper, we present a new large-scale benchmark dataset termed Aerial Imagery for Roof Segmentation (AIRS).
SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
But, this raises an important problem in active vision: given an {\bf infinite} data space, how to effectively sample a {\bf finite} subset to train a visual classifier?
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision
We generate a large synthetic image dataset with automatically computed hazardous regions and analyze algorithms on these regions.
A Hierarchical Distributed Processing Framework for Big Image Data
The proposed ICP framework consists of two mechanisms, i. e. SICP (Static ICP) and DICP (Dynamic ICP).
Data classification using the Dempster-Shafer method
In this paper, the Dempster-Shafer method is employed as the theoretical basis for creating data classification systems.
