Search Results for author:
Found 260 papers, 129 papers with code
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on
Semantic Segmentation
on ADE20K val
Bringing Old Photos Back to Life
Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.
Old Photo Restoration via Deep Latent Space Translation
Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios.
Ranked #14 on
Object Detection
on COCO-O
YOLOv6 v3.0: A Full-Scale Reloading
For a glimpse of performance, our YOLOv6-N hits 37. 5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU.
Ranked #1 on
Object Detection
on COCO 2017 val
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene.
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image.
DeepSeek-VL: Towards Real-World Vision-Language Understanding
The DeepSeek-VL family (both 1. 3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks.
Ranked #28 on
Visual Question Answering
on MM-Vet
Paint by Example: Exemplar-based Image Editing with Diffusion Models
Language-guided image editing has achieved great success recently.
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.
Ranked #1 on
Text-to-Image Generation
on Oxford 102 Flowers
(using extra training data)
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs.
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices.
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance.
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
Deep convolutional neural networks demonstrate impressive results in the super-resolution domain.
Ranked #16 on
Image Super-Resolution
on BSD100 - 2x upscaling
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
We have also contributed the first image composition toolbox: libcom https://github. com/bcmi/libcom, which assembles 10+ image composition related functions (e. g., image blending, image harmonization, object placement, shadow generation, generative composition).
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently.
Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
In this paper, we study the task of training a unified 3D detector from multiple datasets.
SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification
In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model.
ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs.
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
Our contributions are threefold: (1) Occupancy prediction is shown to be promising for learning general representations, which is demonstrated by extensive experiments on plenty of datasets and tasks.
AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks.
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects.
Bringing Old Films Back to Life
We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films.
Ranked #6 on
Analog Video Restoration
on TAPE
StyleSwin: Transformer-based GAN for High-resolution Image Generation
To this end, we believe that local attention is crucial to strike the balance between computational efficiency and modeling capacity.
Ranked #1 on
Image Generation
on CelebA 256x256
(FID metric)
Pretraining is All You Need for Image-to-Image Translation
We propose to use pretraining to boost general image-to-image translation.
Ranked #1 on
Sketch-to-Image Translation
on COCO-Stuff
MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction
This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7, 063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources.
Mining Error Templates for Grammatical Error Correction
We have accumulated 1, 119 error templates for Chinese GEC based on this method.
Cross-domain Correspondence Learning for Exemplar-based Image Translation
The output has the style (e. g., color, texture) in consistency with the semantically corresponding objects in the exemplar.
Ranked #1 on
Image-to-Image Translation
on ADE20K-Outdoor Labels-to-Photos
(FID metric)
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
We present the full-resolution correspondence learning for cross-domain images, which aids image translation.
Deep Exemplar-based Video Colorization
This paper presents the first end-to-end network for exemplar-based video colorization.
Document Rectification and Illumination Correction using a Patch-based CNN
We propose a novel learning method to rectify document images with various distortion types from a single input image.
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
We demonstrate that this is crucial for improving the confidence of models' ranking.
Ranked #3 on
Neural Architecture Search
on CIFAR-10
(using extra training data)
Towards Knowledge-driven Autonomous Driving
This paper explores the emerging knowledge-driven autonomous driving technologies.
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Large language models are built on top of a transformer-based architecture to process textual inputs.
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation.
Ranked #10 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
MoGA: Searching Beyond MobileNetV3
Bearing the target hardware in mind, we propose the first Mobile GPU-Aware (MoGA) neural architecture search in order to be precisely tailored for real-world applications.
Ranked #854 on
Image Classification
on ImageNet
Triple Generative Adversarial Nets
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL).
3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs.
Conditional Positional Encodings for Vision Transformers
Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT).
Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method.
Ranked #24 on
Neural Architecture Search
on CIFAR-10
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w. r. t.
OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving
With the development of implicit rendering technology and in-depth research on using generative models to produce data at scale, we propose OASim, an open and adaptive simulator and autonomous driving data generator based on implicit neural rendering.
Blind Geometric Distortion Correction on Images Through Deep Learning
We propose the first general framework to automatically correct different types of geometric distortion in a single input image.
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search
To discover powerful yet compact models is an important goal of neural architecture search.
Ranked #76 on
Neural Architecture Search
on ImageNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
(Earth Mover's Distance metric)
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously.
FastPillars: A Deployment-friendly Pillar-based 3D Detector
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
Delving into Shape-aware Zero-shot Semantic Segmentation
Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.
Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image.
Ranked #1 on
Aesthetics Quality Assessment
on CADB
ControlCom: Controllable Image Composition using Diffusion Model
To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition.
Performance-aware Approximation of Global Channel Pruning for Multitask CNNs
Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance.
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
Thus, the generation performance on a subset of timesteps is crucial, which is greatly influenced by the covariance design in DPMs.
Disentangled Inference for GANs with Latently Invertible Autoencoder
In this paper, we show that the entanglement of the latent space for the VAE/GAN framework poses the main challenge for encoder learning.
SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser
Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences.
OPA: Object Placement Assessment Dataset
Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e. g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image.
Graphical Generative Adversarial Networks
We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data.
Lenna: Language Enhanced Reasoning Detection Assistant
To evaluate the reasoning capability of Lenna, we construct a ReasonDet dataset to measure its performance on reasoning-based detection.
NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts
We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains.
Ternary Weight Networks
We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1.
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
We call this approach DARTS-.
Ranked #20 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Shadow Generation for Composite Image Using Diffusion model
In the realm of image composition, generating realistic shadow for the inserted foreground remains a formidable challenge.
Adversarial Texture for Fooling Person Detectors in the Physical World
Experiments showed that these clothes could fool person detectors in the physical world.
Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup.
Deep Sketch-guided Cartoon Video Inbetweening
The key idea of the proposed approach is to estimate the dense cross-domain correspondence between the sketch and cartoon video frames, and employ a blending module with occlusion estimation to synthesize the middle frame guided by the sketch.
Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation
Although domain adaptation has been extensively studied in natural image-based segmentation task, the research on cross-domain segmentation for very high resolution (VHR) remote sensing images (RSIs) still remains underexplored.
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.
Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
In SNTG, a graph is constructed based on the predictions of the teacher model, i. e., the implicit self-ensemble of models.
Triple Generative Adversarial Networks
It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).
Microshift: An Efficient Image Compression Algorithm for Hardware
In our method, the image is first micro-shifted, then the sub-quantized values are further compressed.
Fast Deep Matting for Portrait Animation on Mobile Phone
Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps.
Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and RL.
MixPath: A Unified Approach for One-shot Neural Architecture Search
However, current two-stage neural architecture search methods are mainly limited to single-path search spaces.
Improving Seq2Seq Grammatical Error Correction via Decoding Interventions
In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token.
Ranked #1 on
Grammatical Error Correction
on MuCGEC
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.
A Matrix-in-matrix Neural Network for Image Super Resolution
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper layers.
Noisy Differentiable Architecture Search
However, it largely suffers from the well-known performance collapse issue due to the aggregation of skip connections.
Ranked #12 on
Neural Architecture Search
on CIFAR-10
Contrastive Cross-domain Recommendation in Matching
Cross-domain recommendation (CDR) aims to provide better recommendation results in the target domain with the help of the source domain, which is widely used and explored in real-world systems.
Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks
Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency.
Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction
Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types.
A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations
Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines.
Ranked #1 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
Multimodal Emotion Recognition
Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially.
Ranked #4 on
Image Clustering
on Coil-20
Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network
The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods.
Human-centric Image Cropping with Partition-aware and Content-preserving Features
Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task.
Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures.
Max-margin Deep Generative Models
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability.
Foreground Object Search by Distilling Composite Image Feature
Additionally, previous works did not release their datasets, so we contribute two datasets for FOS task: S-FOSD dataset with synthetic composite images and R-FOSD dataset with real composite images.
StructChart: Perception, Structuring, Reasoning for Visual Chart Understanding
Charts are common in literature across different scientific fields, conveying rich information easily accessible to readers.
Ranked #17 on
Chart Question Answering
on ChartQA
(using extra training data)
Pruning from Scratch
Network pruning is an important research field aiming at reducing computational costs of neural networks.
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents
Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.
Fast Lossless Neural Compression with Integer-Only Discrete Flows
In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic.
Collaborative Filtering with User-Item Co-Autoregressive Models
Deep neural networks have shown promise in collaborative filtering (CF).
Function Space Particle Optimization for Bayesian Neural Networks
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature.
Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification
Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences.
UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline
Different from previous studies that only focus on a single adaptation task, UniDA3D can tackle several adaptation tasks in 3D segmentation field, by designing a unified source-and-target active sampling strategy, which selects a maximally-informative subset from both source and target domains for effective model adaptation.
Semi-crowdsourced Clustering with Deep Generative Models
We propose a new approach that includes a deep generative model (DGM) to characterize low-level features of the data, and a statistical relational model for noisy pairwise annotations on its subset.
Aspect-specific Context Modeling for Aspect-based Sentiment Analysis
Extensive experimental results on standard and adversarial benchmarks for SC and OE demonstrate the effectiveness and robustness of the proposed method, yielding new state-of-the-art performance on OE and competitive performance on SC.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Max-Margin Deep Generative Models for (Semi-)Supervised Learning
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability.
Bi-level Score Matching for Learning Energy-based Latent Variable Models
This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem.
Deriving the stellar labels of LAMOST spectra with Stellar LAbel Machine (SLAM)
To illustrate this capability, we test the performance of SLAM on stars ranging from Teff$\sim$4000 to $\sim$8000 K trained on LAMOST spectra and stellar labels.
Solar and Stellar Astrophysics Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.
Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
Understanding and Stabilizing GANs' Training Dynamics with Control Theory
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Ranked #37 on
Image Generation
on CIFAR-10
(Inception score metric)
Textbook Question Answering Under Instructor Guidance With Memory Networks
The machine thus performs as an instructor to extract the essay-level contradictions as the Guidance.
LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps).
A Closer Look at Few-Shot 3D Point Cloud Classification
In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes.
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable.
HCGrid: A Convolution-based Gridding Framework for RadioAstronomy in Hybrid Computing Environments
Gridding operation, which is to map non-uniform data samples onto a uniformly distributedgrid, is one of the key steps in radio astronomical data reduction process.
Instrumentation and Methods for Astrophysics
Estimating the Causal Effect of Early ArXiving on Paper Acceptance
However, since quality is a challenging construct to estimate, we use the negative outcome control method, using paper citation count as a control variable to debias the quality confounding effect.
Learning to Generate with Memory
Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at inferring high-level invariant representations from unlabeled data.
Multi-objects Generation with Amortized Structural Regularization
Deep generative models (DGMs) have shown promise in image generation.
Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure
Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights.
Automatic, Dynamic, and Nearly Optimal Learning Rate Specification by Local Quadratic Approximation
In each update step, given the gradient direction, we locally approximate the loss function by a standard quadratic function of the learning rate.
OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details.
Deep Bayesian Structure Networks
Bayesian neural networks (BNNs) introduce uncertainty estimation to deep networks by performing Bayesian inference on network weights.
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks
The first stage of ROCK corresponds to the process of decomposing objects into parts in human vision.
Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint.
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage.
MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization
Based on this, we propose a relative structural entropy-based position encoding and a multi-head attention masking scheme based on multi-layer encoding trees.
Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics.
Permutation-equivariant and Proximity-aware Graph Neural Networks with Stochastic Message Passing
Graph neural networks (GNNs) are emerging machine learning models on graphs.
Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
Our results can explain some mysterious behaviours of the bilevel programming in practice, for instance, overfitting to the validation set.
Language-Driven Anchors for Zero-Shot Adversarial Robustness
Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial robustness an open question.
ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
To overcome this challenge, we propose an innovative multimodal framework, called ZRIGF, which assimilates image-grounded information for dialogue generation in zero-resource situations.
Semantic Cluster Unary Loss for Efficient Deep Hashing
The resultant hashcodes form several compact clusters, which means hashcodes in the same cluster have similar semantic information.
Message Passing Stein Variational Gradient Descent
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods.
Interlinked Convolutional Neural Networks for Face Parsing
It amounts to labeling each pixel with appropriate facial parts such as eyes and nose.
Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition
The layers between the source and target feature extractor are partially untied during the training stage to take both training efficiency and domain adaptation into consideration.
SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation.
PBODL : Parallel Bayesian Online Deep Learning for Click-Through Rate Prediction in Tencent Advertising System
Then we extend the model family to a variety of bayesian online models with increasing feature embedding capabilities, such as Sparse-MLP, FM-MLP and FFM-MLP.
Improving Interpretability of Deep Neural Networks with Semantic Information
Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems.
Big Learning with Bayesian Methods
Explosive growth in data and availability of cheap computing resources have sparked increasing interest in Big learning, an emerging subfield that studies scalable machine learning algorithms, systems, and applications with Big Data.
Effective Deterministic Initialization for $k$-Means-Like Methods via Local Density Peaks Searching
Based on these two components, we search for the local density peaks which are characterized with high local densities and high LDIs to deal with 1) and 2).
Fast Sampling for Bayesian Max-Margin Models
Bayesian max-margin models have shown superiority in various practical applications, such as text categorization, collaborative prediction, social network link prediction and crowdsourcing, and they conjoin the flexibility of Bayesian modeling and predictive strengths of max-margin learning.
Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
Hashing method maps similar data to binary hashcodes with smaller hamming distance, and it has received a broad attention due to its low storage cost and fast retrieval speed.
Bootstrapping Face Detection with Hard Negative Examples
Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks.
A New Manifold Distance Measure for Visual Object Categorization
The proposed distance is more robust to rotations and translations of images than the traditional manifold distance and the CW-SSIM index based distance.
A Novel Biologically Mechanism-Based Visual Cognition Model--Automatic Extraction of Semantics, Formation of Integrated Concepts and Re-selection Features for Ambiguity
In general, the robustness and precision of recognition is one of the key problems for object recognition models.
Learning Deep Generative Models with Doubly Stochastic MCMC
We present doubly stochastic gradient MCMC, a simple and generic method for (approximate) Bayesian inference of deep generative models (DGMs) in a collapsed continuous parameter space.
Fast Parallel SVM using Data Augmentation
As one of the most popular classifiers, linear SVMs still have challenges in dealing with very large-scale problems, even though linear or sub-linear algorithms have been developed recently on single machines.
Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation
We present a discriminative nonparametric latent feature relational model (LFRM) for link prediction to automatically infer the dimensionality of latent features.
Jointly Modeling Topics and Intents with Global Order Structure
Modeling document structure is of great importance for discourse analysis and related applications.
Dropout Training for Support Vector Machines
To deal with the intractable expectation of the non-smooth hinge loss under corrupting distributions, we develop an iteratively re-weighted least square (IRLS) algorithm by exploring data augmentation techniques.
Gibbs Max-margin Topic Models with Data Augmentation
Gibbs max-margin supervised topic models minimize an expected margin loss, which is an upper bound of the existing margin loss derived from an expected prediction rule.
Discriminative Relational Topic Models
Many scientific and engineering fields involve analyzing network data.
Improved Bayesian Logistic Supervised Topic Models with Data Augmentation
Supervised topic models with a logistic likelihood have two issues that potentially limit their practical use: 1) response variables are usually over-weighted by document word counts; and 2) existing variational inference methods make strict mean-field assumptions.
Deep Structured Generative Models
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures.
Learning Implicit Generative Models by Teaching Explicit Ones
Implicit generative models are difficult to train as no explicit density functions are defined.
A Unified Framework for Community Detection and Network Representation Learning
Network representation learning (NRL) aims to learn low-dimensional vectors for vertices in a network.
Social and Information Networks Physics and Society
An Unified Intelligence-Communication Model for Multi-Agent System Part-I: Overview
Motivated by Shannon's model and recent rehabilitation of self-supervised artificial intelligence having a "World Model", this paper propose an unified intelligence-communication (UIC) model for describing a single agent and any multi-agent system.
The Entropy of Artificial Intelligence and a Case Study of AlphaZero from Shannon's Perspective
Firstly, as there is a finite number of possibilities in the game, is there a quantifiable intelligence measurement for evaluating intelligent systems, e. g. AlphaZero?
COSINE: Compressive Network Embedding on Large-scale Information Networks
There is recently a surge in approaches that learn low-dimensional embeddings of nodes in networks.
Supervised Treebank Conversion: Data and Approaches
Treebank conversion is a straightforward and effective way to exploit various heterogeneous treebanks for boosting parsing performance.
DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning
Based on these sub-images, a local exposure for each sub-image is automatically learned by virtue of policy network sequentially while the reward of learning is globally designed for striking a balance of overall exposures.
Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling
We adopt a deep recurrent convolutional neural network (RCNN) for this task, which is originally proposed for object recognition.
Distributed Bayesian Posterior Sampling via Moment Sharing
We propose a distributed Markov chain Monte Carlo (MCMC) inference algorithm for large scale Bayesian posterior simulation.
Scalable Inference for Logistic-Normal Topic Models
Logistic-normal topic models can effectively discover correlation structures among latent topics.
Super-Bit Locality-Sensitive Hashing
Sign-random-projection locality-sensitive hashing (SRP-LSH) is a probabilistic dimension reduction method which provides an unbiased estimate of angular similarity, yet suffers from the large variance of its estimation.
Partially Observed Maximum Entropy Discrimination Markov Networks
Learning graphical models with hidden variables can offer semantic insights to complex data and lead to salient structured predictors without relying on expensive, sometime unattainable fully annotated training data.
Interpret Neural Networks by Identifying Critical Data Routing Paths
Interpretability of a deep neural network aims to explain the rationale behind its decisions and enable the users to understand the intelligent agents, which has become an important issue due to its importance in practical applications.
To Relieve Your Headache of Training an MRF, Take AdVIL
We propose a black-box algorithm called {\it Adversarial Variational Inference and Learning} (AdVIL) to perform inference and learning on a general Markov random field (MRF).
Orientational Pyramid Matching for Recognizing Indoor Scenes
The novelty lies in that OPM uses the 3D orientations to form the pyramid and produce the pooling regions, which is unlike SPM that uses the spatial positions to form the pyramid.
RIDE: Reversal Invariant Descriptor Enhancement
In many fine-grained object recognition datasets, image orientation (left/right) might vary from sample to sample.
Pairwise Teacher-Student Network for Semi-Supervised Hashing
Hashing method maps similar high-dimensional data to binary hashcodes with smaller hamming distance, and it has received broad attention due to its low storage cost and fast retrieval speed.
Artificial Intelligence in Intelligent Tutoring Robots: A Systematic Review and Design Guidelines
We first analyse the environment of the ITR and propose a relationship model for describing interactions of ITR with the students, the social milieu and the curriculum.
Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction
To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i. e., high-level agent and low-level agent.
Hierarchical Reinforcement Learning
Recommendation Systems
+2
Learning Semantic Vector Representations of Source Code via a Siamese Neural Network
The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code.
Curriculum Learning for Deep Generative Models with Clustering
The experiments on cat and human-face data validate that our algorithm is able to learn the optimal generative models (e. g. ProGAN) with respect to specified quality metrics for noisy data.
Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.
A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks
Intensive computation is entering data centers with multiple workloads of deep learning.
Hierarchy Response Learning for Neural Conversation Generation
Specifically, a hierarchical response generation (HRG) framework is proposed to capture the conversation intention in a natural and coherent way.
Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction
In deep CTR models, exploiting users' historical data is essential for learning users' behaviors and interests.
In Vitro Fertilization (IVF) Cumulative Pregnancy Rate Prediction from Basic Patient Characteristics
Tens of millions of women suffer from infertility worldwide each year.
Automatic quality assessment for 2D fetal sonographic standard plane based on multi-task learning
An essential criterion for FS image quality control is that all the essential anatomical structures in the section should appear full and remarkable with a clear boundary.
Realization of spatial sparseness by deep ReLU nets with massive data
The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality.
Latent Variables on Spheres for Autoencoders in High Dimensions
Variational Auto-Encoder (VAE) has been widely applied as a fundamental generative model in machine learning.
Neural Architecture Search on Acoustic Scene Classification
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden.
User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization
According to our analysis, the UDP framework can realize $(\epsilon_{i}, \delta_{i})$-LDP for the $i$-th MT with adjustable privacy protection levels by varying the variances of the artificial noise processes.
Perceptual Image Super-Resolution with Progressive Adversarial Network
Progressive growing enhances image resolution gradually, thereby preserving precision of recovered image.
Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks
The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory.
A Unified Mixture-View Framework for Unsupervised Representation Learning
Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augmentation.
Sex Differences in Severity and Mortality Among Patients With COVID-19: Evidence from Pooled Literature Analysis and Insights from Integrated Bioinformatic Analysis
Objective: To conduct a meta-analysis of current studies that examined sex differences in severity and mortality in patients with COVID-19, and identify potential mechanisms underpinning these differences.
Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2
Their location in [$\alpha$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$\alpha$/M] \textbf{lower} than the thick disk.
Astrophysics of Galaxies
Robust Dynamical Decoupling for the Manipulation of a Spin Network via a Single Spin
High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.
Quantum Physics
The Flare and Warp of the Young Stellar Disk traced with LAMOST DR5 OB-type stars
We present analysis of the spatial density structure for the outer disk from 8$-$14 \, kpc with the LAMOST DR5 13534 OB-type stars and observe similar flaring on north and south sides of the disk implying that the flaring structure is symmetrical about the Galactic plane, for which the scale height at different Galactocentric distance is from 0. 14 to 0. 5 \, kpc.
Astrophysics of Galaxies
Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network
In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity.
AutoKWS: Keyword Spotting with Differentiable Architecture Search
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption.
A Minimax Probability Machine for Non-Decomposable Performance Measures
On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the accuracy rate, which makes it unsuitable to deal with imbalanced classification tasks.
Learning with Smooth Hinge Losses
Due to the non-smoothness of the Hinge loss in SVM, it is difficult to obtain a faster convergence rate with modern optimization algorithms.
Extragalactic HI 21-cm absorption line observations with the Five-hundred-meter Aperture Spherical radio Telescope
Our observations successfully confirmed the existence of HI absorption lines in all these systems, including two sources that were marginally detected by ALFALFA.
Astrophysics of Galaxies
MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks.
Free-Space Optical Communication Using Non-mode-Selective Photonic Lantern Based Coherent Receiver
A free-space optical communication system using non-mode-selective photonic lantern (PL) based coherent receiver is studied.
Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable
Estimating dynamic treatment regimes (DTRs) from retrospective observational data is challenging as some degree of unmeasured confounding is often expected.
Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.
