Search Results for author:
Found 295 papers, 109 papers with code
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation
With ResNet50 backbone, our MaskConver achieves 53. 6% PQ on the COCO panoptic val set, outperforming the modern convolution-based model, Panoptic FCN, by 9. 3% as well as transformer-based models such as Mask2Former (+1. 7% PQ) and kMaX-DeepLab (+0. 6% PQ).
Ranked #8 on
Panoptic Segmentation
on COCO test-dev
MobileNetV4 - Universal Models for the Mobile Ecosystem
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices.
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts
Instead of compressing multiple tasks' knowledge into a single model, MoE separates the parameter space and only utilizes the relevant model pieces given task type and its input, which provides stabilized MTL training and ultra-efficient inference.
Tutel: Adaptive Mixture-of-Experts at Scale
On efficiency, Flex accelerates SwinV2-MoE, achieving up to 1. 55x and 2. 11x speedup in training and inference over Fairseq, respectively.
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
Data-centric Artificial Intelligence: A Survey
Artificial Intelligence (AI) is making a profound impact in almost every domain.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Towards Fast, Accurate and Stable 3D Dense Face Alignment
Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.
Ranked #1 on
3D Face Reconstruction
on Florence
(Mean NME metric)
Acme: A Research Framework for Distributed Reinforcement Learning
These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.
Data-centric AI: Perspectives and Challenges
The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability.
NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion
To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder framework is designed, which can not only deal with videos as 3D data but also adapt to texts and images as 1D and 2D data, respectively.
Ranked #1 on
Text-to-Video Generation
on Kinetics
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations
Understanding clothes from a single image has strong commercial and cultural impacts on modern societies.
Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
To demonstrate the superiority and generality of the proposed method, we evaluate the proposed method on five crack datasets and compare it with state-of-the-art crack detection, edge detection, semantic segmentation methods.
Low-bit Quantization of Neural Networks for Efficient Inference
Recent machine learning methods use increasingly large deep neural networks to achieve state of the art results in various tasks.
Make Skeleton-based Action Recognition Model Smaller, Faster and Better
Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed.
Ranked #1 on
Hand Gesture Recognition
on DHG-14
BitNet: Scaling 1-bit Transformers for Large Language Models
The increasing size of large language models has posed challenges for deployment and raised concerns about environmental impact due to high energy consumption.
Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years.
Ranked #1 on
Image Retrieval
on Par6k
Differentiable Learning of Logical Rules for Knowledge Base Reasoning
We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model.
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background.
Good Semi-supervised Learning that Requires a Bad GAN
Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time.
Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads
With widespread advances in machine learning, a number of large enterprises are beginning to incorporate machine learning models across a number of products.
Distributed, Parallel, and Cluster Computing
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.
CAT: Cross Attention in Vision Transformer
In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information.
Clustered Object Detection in Aerial Images
The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet).
Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking
In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking.
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark
The average video length of LaSOT is around 2, 500 frames, where each video contains various challenge factors that exist in real world video footage, such as the targets disappearing and re-appearing.
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity.
Ranked #9 on
Video Retrieval
on MSVD
(using extra training data)
Student Classroom Behavior Detection based on YOLOv7-BRA and Multi-Model Fusion
We constructed a dataset, which contained 11, 248 labels and 4, 001 images, with an emphasis on the common behavior of raising hands in a classroom setting (Student Classroom Behavior dataset, SCB-Dataset).
Student Classroom Behavior Detection based on Improved YOLOv7
Accurately detecting student behavior in classroom videos can aid in analyzing their classroom performance and improving teaching effectiveness.
SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior
The use of deep learning methods to automatically detect students' classroom behavior is a promising approach for analyzing their class performance and improving teaching effectiveness.
Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion
To address this issue, we proposed a method for extending the spatio-temporal behavior dataset in Student Classroom Scenarios (SCB-ST-Dataset4) through image dataset.
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied.
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
In this paper, we introduce XGLUE, a new benchmark dataset that can be used to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora and evaluate their performance across a diverse set of cross-lingual tasks.
A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions
Spatio-temporal action detection is an important and challenging problem in video understanding.
A large-scale dataset for end-to-end table recognition in the wild
To this end, we propose a new large-scale dataset named Table Recognition Set (TabRecSet) with diverse table forms sourcing from multiple scenarios in the wild, providing complete annotation dedicated to end-to-end TR research.
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers.
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.
Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance.
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.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models
More importantly, we present $\textbf{Griffon}$, a purely LVLM-based baseline, which does not require the introduction of any special tokens, expert models, or additional detection modules.
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpass the performance of task-specific experts in complex and dense scenarios.
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.
Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification
To the best of our knowledge, this is the first work to jointly model both feature and modality variation for different samples to provide trustworthy fusion in multi-modal classification.
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.
Cascade Graph Neural Networks for RGB-D Salient Object Detection
Current works either simply distill prior knowledge from the corresponding depth map for handling the RGB-image or blindly fuse color and geometric information to generate the coarse depth-aware representations, hindering the performance of RGB-D saliency detectors. In this work, we introduceCascade Graph Neural Networks(Cas-Gnn), a unified framework which is capable of comprehensively distilling and reasoning the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.
Ranked #5 on
RGB-D Salient Object Detection
on NJU2K
Mutual Graph Learning for Camouflaged Object Detection
Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models.
Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
We employ a probing technique to extract representations from different layers of the model and apply these to classification tasks.
XDeep: An Interpretation Tool for Deep Neural Networks
XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers.
MlTr: Multi-label Classification with Transformer
The task of multi-label image classification is to recognize all the object labels presented in an image.
Ranked #12 on
Multi-Label Classification
on MS-COCO
Learning Optical Flow with Adaptive Graph Reasoning
Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph.
RGB-Event Fusion for Moving Object Detection in Autonomous Driving
Moving Object Detection (MOD) is a critical vision task for successfully achieving safe autonomous driving.
Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms
The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks.
Event-Free Moving Object Segmentation from Moving Ego Vehicle
Subsequently, we devise EmoFormer, a novel network able to exploit the event data.
Learning Optical Flow With Kernel Patch Attention
Optical flow is a fundamental method used for quantitative motion estimation on the image plane.
OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields
This paper proposes a novel object-removing pipeline, named OR-NeRF, that can remove objects from 3D scenes with user-given points or text prompts on a single view, achieving better performance in less time than previous works.
GAFlow: Incorporating Gaussian Attention into Optical Flow
Moreover, for reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM) which not only inherits properties from Gaussian distribution to instinctively revolve around the neighbor fields of each point but also is empowered to put the emphasis on contextually related regions during matching.
Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate
3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point cloud data.
Ranked #1 on
Multi-Object Tracking
on MOT15_3D
(using extra training data)
Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses.
GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation.
Ranked #16 on
Text-to-Video Generation
on MSR-VTT
(CLIPSIM metric)
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design
In each iteration, the multi-objective optimization of the multiple acquisition functions is performed to search for the Pareto front of the acquisition functions.
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection
Spotting objects that are visually adapted to their surroundings is challenging for both humans and AI.
DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research
The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research.
Contour Knowledge Transfer for Salient Object Detection
Our goal is to overcome this limitation by automatically converting an existing deep contour detection model into a salient object detection model without using any manual salient object masks.
DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration
In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration.
Forecasting Human Trajectory from Scene History
We categorize scene history information into two types: historical group trajectory and individual-surroundings interaction.
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
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.
ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification
We evaluate ReMix on two public datasets with two state-of-the-art MIL methods.
SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection
To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection.
Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system.
UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup
Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset.
Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences
We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA).
Accelerating Shapley Explanation via Contributive Cooperator Selection
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity.
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
As a pioneering exploration that expands event detection to the scenarios involving informal and heterogeneous texts, we propose a new large-scale Chinese event detection dataset based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.
Exploring Stochastic Autoregressive Image Modeling for Visual Representation
By introducing stochastic prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling.
Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval
Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i. e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i. e., target domain).
Ranked #1 on
Image Retrieval
on PKU-Reid
PIER: Permutation-Level Interest-Based End-to-End Re-ranking Framework in E-commerce
Then we design a novel omnidirectional attention mechanism in OCPM to capture the context information in the permutation.
Probabilistic Model Distillation for Semantic Correspondence
We address this problem with the use of a novel Probabilistic Model Distillation (PMD) approach which transfers knowledge learned by a probabilistic teacher model on synthetic data to a static student model with the use of unlabeled real image pairs.
CoRTX: Contrastive Framework for Real-time Explanation
In this work, we propose a COntrastive Real-Time eXplanation (CoRTX) framework to learn the explanation-oriented representation and relieve the intensive dependence of explainer training on explanation labels.
AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation
We evaluate our approach on the photographic ancient character datasets, e. g., OBC306 and CSDD.
DEGREE: Decomposition Based Explanation For Graph Neural Networks
Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data.
Application of SsVGMM to medical data-classification with novelty detection
There is a considerable demand to apply classification in medical analysis.
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.
Generalized Demographic Parity for Group Fairness
We show the understanding of GDP from the probability perspective and theoretically reveal the connection between GDP regularizer and adversarial debiasing.
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks
This paradigm is often impractical in real-world applications since online dialogue systems usually involve continually emerging new data and domains.
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
By using MOT, the spatiotemporal boundary of each actor is obtained and assigned to a unique actor identity.
DESED: Dialogue-based Explanation for Sentence-level Event Detection
Many recent sentence-level event detection efforts focus on enriching sentence semantics, e. g., via multi-task or prompt-based learning.
LODE: Deep Local Deblurring and A New Benchmark
While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake.
Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices
Experimental studies with 20 participants demonstrate that, thanks to the emotionship awareness, EMOShip not only achieves superior emotion recognition accuracy over existing methods (80. 2% vs. 69. 4%), but also provides a valuable understanding of the cause of emotions.
Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks.
Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems
Technological breakthroughs allow us to collect data with increasing spatio-temporal resolution from complex interaction systems.
Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features
Satirical news is considered to be entertainment, but it is potentially deceptive and harmful.
ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
Interpreting human actions requires understanding the spatial and temporal context of the scenes.
One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstruction
We demonstrate that training DL models on synthetic data, coupled with enhanced learning techniques, yields in vivo MRI reconstructions comparable to or surpassing those of models trained on matched realistic datasets, reducing the reliance on real-world MRI data by up to 96%.
Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles
Gradient boosting of prediction rules is an efficient approach to learn potentially interpretable yet accurate probabilistic models.
Improving Generalization of Metric Learning via Listwise Self-distillation
Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones.
Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking
To overcome this challenge, we introduce a clean-label backdoor watermarking framework that uses imperceptible perturbations to replace mislabeled samples.
Large-scale Bisample Learning on ID Versus Spot Face Recognition
In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition.
Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking
In this paper, we propose a novel tracklet processing method to cleave and re-connect tracklets on crowd or long-term occlusion by Siamese Bi-Gated Recurrent Unit (GRU).
Ranked #20 on
Multi-Object Tracking
on MOT16
Learning to Organize Knowledge and Answer Questions with N-Gram Machines
Though deep neural networks have great success in natural language processing, they are limited at more knowledge intensive AI tasks, such as open-domain Question Answering (QA).
Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection
In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks.
TensorLog: Deep Learning Meets Probabilistic DBs
We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano.
Visual Search at eBay
We harness the availability of large image collection of eBay listings and state-of-the-art deep learning techniques to perform visual search at scale.
Exploiting Local Features from Deep Networks for Image Retrieval
Deep convolutional neural networks have been successfully applied to image classification tasks.
Privacy-Protective-GAN for Face De-identification
In this paper, we propose a new framework called Privacy-Protective-GAN (PP-GAN) that adapts GAN with novel verificator and regulator modules specially designed for the face de-identification problem to ensure generating de-identified output with retained structure similarity according to a single input.
Adversarial Learning for Fine-grained Image Search
Fine-grained image search is still a challenging problem due to the difficulty in capturing subtle differences regardless of pose variations of objects from fine-grained categories.
Using Randomness to Improve Robustness of Machine-Learning Models Against Evasion Attacks
Machine learning models have been widely used in security applications such as intrusion detection, spam filtering, and virus or malware detection.
Attention Driven Person Re-identification
Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc.
Attending Sentences to detect Satirical Fake News
Satirical news detection is important in order to prevent the spread of misinformation over the Internet.
Leveraging Multiple Domains for Sentiment Classification
In addition, the learned feature representation can be used as classifier since our model defines the meaning of feature value and arranges high-level features in a prefixed order, so it is not necessary to train another classifier on top of the new features.
LEARNING TO ORGANIZE KNOWLEDGE WITH N-GRAM MACHINES
Existing end-to-end deep QA models (Miller et al., 2016; Weston et al., 2014) need to read the entire text after observing the question, and therefore their complexity in responding a question is linear in the text size.
Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers
In this paper, we investigate two new strategies to detect objects accurately and efficiently using deep convolutional neural network: 1) scale-dependent pooling and 2) layer-wise cascaded rejection classifiers.
Object-Aware Dense Semantic Correspondence
To address these problems, this paper proposes an object-aware method to estimate per-pixel correspondences from semantic to low-level by learning a classifier for each selected discriminative grid cell and guiding the localization of every pixel under the semantic constraint.
Multi-Task Learning With Low Rank Attribute Embedding for Person Re-Identification
Since attributes are generally correlated, we introduce a low rank attribute embedding into the MTL formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered to better describe people.
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text.
Optimal Control of Complex Systems through Variational Inference with a Discrete Event Decision Process
However, such real-world complex system control is difficult to achieve because of high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decision maker.
Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation
In this paper, we propose to decompose the single segmentation task into three subsequent sub-tasks, including (1) pixel-wise image segmentation, (2) prediction of the class labels of the objects within the image, and (3) classification of the scene the image belonging to.
Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning
In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process.
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
XFake: Explainable Fake News Detector with Visualizations
In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility.
Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification
Interactions among users on social network platforms are usually positive, constructive and insightful.
Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
Learning Credible Deep Neural Networks with Rationale Regularization
Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions.
Fairness in Deep Learning: A Computational Perspective
Deep learning is increasingly being used in high-stake decision making applications that affect individual lives.
GLA-Net: An Attention Network with Guided Loss for Mismatch Removal
To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly.
Contextual Local Explanation for Black Box Classifiers
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.
TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation
In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story.
A Hierarchical Mixture Density Network
One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping.
TracKlinic: Diagnosis of Challenge Factors in Visual Tracking
For the analysis component, given the tracking results on all sequences, it investigates the behavior of the tracker under each individual factor and generates the report automatically.
Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network
Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis.
Detecting Unknown Behaviors by Pre-defined Behaviours: An Bayesian Non-parametric Approach
An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process.
Dually Supervised Feature Pyramid for Object Detection and Segmentation
Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem.
Game Design for Eliciting Distinguishable Behavior
The ability to inferring latent psychological traits from human behavior is key to developing personalized human-interacting machine learning systems.
Relational State-Space Model for Stochastic Multi-Object Systems
Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other.
Hybrid Graph Neural Networks for Crowd Counting
In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph.
Time Series Data Augmentation for Deep Learning: A Survey
In this paper, we systematically review different data augmentation methods for time series.
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents.
Ranked #12 on
Trajectory Prediction
on Stanford Drone
Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild
To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios.
MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
Blur detection is the separation of blurred and clear regions of an image, which is an important and challenging task in computer vision.
Defending SVMs against Poisoning Attacks: the Hardness and DBSCAN Approach
For the data sanitization defense, we link it to the intrinsic dimensionality of data; in particular, we provide a sampling theorem in doubling metrics for explaining the effectiveness of DBSCAN (as a density-based outlier removal method) for defending against poisoning attacks.
Birds of a Feather Flock Together: Satirical News Detection via Language Model Differentiation
In this work, we propose a method that differentiates the satirical news and true news.
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement.
Ranked #1 on
Multi-Object Tracking
on MOTS20
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+2
Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry
We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA).
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Combating fake news and misinformation propagation is a challenging task in the post-truth era.
PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognition
Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected by illumination and season changes, LIDAR cannot get the rich data as the image could , In this paper, we propose the PIC-Net (Point cloud and Image Collaboration Network), which use attention mechanism to fuse the features of image and point cloud, and mine the complementary information between the two.
Ranked #2 on
Visual Place Recognition
on Oxford RobotCar (LiDAR 4096 points+RGB)
(recall@top1% metric)
Linear-time Temporal Logic with Team Semantics: Expressivity and Complexity
We study the expressivity and complexity of model checking linear temporal logic with team semantics (TeamLTL).
Logic in Computer Science Computational Complexity F.4.1; D.2.4
Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers
Intuitively, the transfer effect from one task to another task depends on dataset shifts such as sample sizes and covariance matrices.
Tricritical physics in two-dimensional $p$-wave superfluids
When strong quantum fluctuations near resonance are taken into account, the line of continuous phase transitions terminates at two multicritical points near resonance, between which the transitions are expected to be first-order ones.
Quantum Gases
Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification
To recognize unseen relations at test time, we explore the problem of zero-shot relation classification.
Bayesian Multi-type Mean Field Multi-agent Imitation Learning
We demonstrate the performance of our algorithm through benchmarking with three state-of-the-art multi-agent imitation learning algorithms on several tasks, including solving a multi-agent traffic optimization problem in a real-world transportation network.
Fault-Aware Robust Control via Adversarial Reinforcement Learning
Robots have limited adaptation ability compared to humans and animals in the case of damage.
XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation
In this paper, we introduce XGLUE, a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora, and evaluate their performance across a diverse set of cross-lingual tasks.
Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution
In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM).
Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems
Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline.
A Polynomial Roth Theorem for Corners in Finite Fields
We prove a Roth type theorem for polynomial corners in the finite field setting.
Classical Analysis and ODEs Combinatorics Number Theory
Possible evidence of hydrogen emission in the first-overtone and multi-mode RR Lyrae variables
The nature of shock waves in non-fundamental mode RR Lyrae stars remains a mystery because of limited spectroscopic observations.
Solar and Stellar Astrophysics
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios.
Sample canonical correlation coefficients of high-dimensional random vectors with finite rank correlations
If the entries of $\mathbf x$, $\mathbf y$ and $\mathbf z$ are i. i. d.
Probability
Superresolving second-order correlation imaging using synthesized colored noise speckles
We present a novel method to synthesize non-trivial speckles that can enable superresolving second-order correlation imaging.
Optics Image and Video Processing
Improving Authorship Verification using Linguistic Divergence
It is also one of the first to use Deep Language Models in this setting.
CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changes
Garment transfer shows great potential in realistic applications with the goal of transfering outfits across different people images.
Calibrating multi-dimensional complex ODE from noisy data via deep neural networks
Our method is able to recover the ODE system without being subject to the curse of dimensionality and complicated ODE structure.
MST: Masked Self-Supervised Transformer for Visual Representation
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly.
Model-Based Counterfactual Synthesizer for Interpretation
To address these limitations, we propose a Model-based Counterfactual Synthesizer (MCS) framework for interpreting machine learning models.
A Scalable 256-Elements E-Band Phased-Array Transceiver for Broadband Communication
For E-band wireless communications, a high gain steerable antenna with sub-arrays is desired to reduce the implementation complexity.
An Efficient Asynchronous Batch Bayesian Optimization Approach for Analog Circuit Synthesis
A new strategy is proposed to better balance the exploration and exploitation and guarantee the diversity of the query points.
An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble
After achieving the first feasible point, we favor the feasible region by adopting a specially designed penalization term to the acquisition function ensemble.
Opinion Prediction with User Fingerprinting
Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.
RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting
Motion forecasting plays a significant role in various domains (e. g., autonomous driving, human-robot interaction), which aims to predict future motion sequences given a set of historical observations.
Density-Based Dynamic Curriculum Learning for Intent Detection
To handle this problem, we propose a density-based dynamic curriculum learning model.
Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence.
Adaptive Label Smoothing To Regularize Large-Scale Graph Training
Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.
LinEasyBO: Scalable Bayesian Optimization Approach for Analog Circuit Synthesis via One-Dimensional Subspaces
A large body of literature has proved that the Bayesian optimization framework is especially efficient and effective in analog circuit synthesis.
Predicting Personal Opinion on Future Events with Fingerprints
We evaluate the proposed model on this dataset.
Actuarial-consistency and two-step actuarial valuations: a new paradigm to insurance valuation
This paper introduces new valuation schemes called actuarial-consistent valuations for insurance liabilities which depend on both financial and actuarial risks, which imposes that all actuarial risks are priced via standard actuarial principles.
Causal-TGAN: Causally-Aware Synthetic Tabular Data Generative Adversarial Network
The flexibility of this architecture is its capability to support different types of expert knowledge (e. g., complete or partial) about the causal nature of the underlying phenomenon.
EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression
Based on the implementation, we propose a memory-efficient framework called ``EXACT'', which for the first time demonstrate the potential and evaluate the feasibility of training GNNs with compressed activations.
Defense Against Explanation Manipulation
Explainable machine learning attracts increasing attention as it improves transparency of models, which is helpful for machine learning to be trusted in real applications.
Towards Privacy-Preserving Affect Recognition: A Two-Level Deep Learning Architecture
Possible solutions to protect the privacy of users and avoid misuse of their identities are to: (1) extract anonymised facial features, namely action units (AU) from a database of images, discard the images and use AUs for processing and training, and (2) federated learning (FL) i. e. process raw images in users' local machines (local processing) and send the locally trained models to the main processing machine for aggregation (central processing).
Improving Evidence Retrieval with Claim-Evidence Entailment
Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim.
Neural Born Iteration Method For Solving Inverse Scattering Problems: 2D Cases
In this paper, we propose the neural Born iterative method (NeuralBIM) for solving 2D inverse scattering problems (ISPs) by drawing on the scheme of physics-informed supervised residual learning (PhiSRL) to emulate the computing process of the traditional Born iterative method (TBIM).
BBA-net: A bi-branch attention network for crowd counting
Our method can integrate the pedestrian's head and body information to enhance the feature expression ability of the density map.
A comprehensive benchmark analysis for sand dust image reconstruction
In this paper, we presented a comprehensive perceptual study and analysis of real-world sand dust images, then constructed a Sand-dust Image Reconstruction Benchmark (SIRB) for training Convolutional Neural Networks (CNNs) and evaluating algorithms performance.
Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification
We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss
Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.
Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model
Traditional machine learning approaches capture complex system dynamics either with dynamic Bayesian networks and state space models, which is hard to scale because it is non-trivial to prescribe the dynamics with a sparse graph or a system of differential equations; or a deep neural networks, where the distributed representation of the learned dynamics is hard to interpret.
