Search Results for author:
Found 342 papers, 133 papers with code
Toward Knowledge-Enriched Conversational Recommendation Systems
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods.
Adapting LLaMA Decoder to Vision Transformer
We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a casual mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training.
TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
However, the clothing identity uncontrollability and training inefficiency of existing diffusion-based methods, which struggle to maintain the identity even with full parameter training, are significant limitations that hinder the widespread applications.
DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centered images, novel challenges arise with a nuanced task of "identity fine editing": precisely modifying specific features of a subject while maintaining its inherent identity and context.
END4Rec: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation
In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing.
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness.
Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage.
SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction.
Exploring Task Unification in Graph Representation Learning via Generative Approach
Specifically, GA^2E proposes to use the subgraph as the meta-structure, which remains consistent across all graph tasks (ranging from node-, edge-, and graph-level to transfer learning) and all stages (both during training and inference).
Tuning-Free Image Customization with Image and Text Guidance
To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions.
HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching
Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.
Interactive $360^{\circ}$ Video Streaming Using FoV-Adaptive Coding with Temporal Prediction
We develop a low-latency FoV-adaptive coding and streaming system for interactive applications that is robust to bandwidth variations and FoV prediction errors.
AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network.
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion.
RLPeri: Accelerating Visual Perimetry Test with Reinforcement Learning and Convolutional Feature Extraction
During the test, a patient's gaze is fixed at a specific location while light stimuli of varying intensities are presented in central and peripheral vision.
LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking
Deep learning models, particularly those based on transformers, often employ numerous stacked structures, which possess identical architectures and perform similar functions.
The 2nd Workshop on Recommendation with Generative Models
The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations.
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Experimentally, TimeXer significantly improves time series forecasting with exogenous variables and achieves consistent state-of-the-art performance in twelve real-world forecasting benchmarks.
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
While fine-tuning large language models (LLMs) for specific tasks often yields impressive results, it comes at the cost of memory inefficiency due to back-propagation in gradient-based training.
Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization
We explore the typical data characteristics and optimization statistics of CTR prediction, revealing a strong positive correlation between the top hessian eigenvalue and feature frequency.
Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices
Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data.
Aligning Crowd Feedback via Distributional Preference Reward Modeling
In this paper, we introduce the Distributional Preference Reward Model (DPRM), a simple yet effective framework to align large language models with a diverse set of human preferences.
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
Foundation models of time series have not been fully developed due to the limited availability of large-scale time series and the underexploration of scalable pre-training.
Timer: Transformers for Time Series Analysis at Scale
Continuous progresses have been achieved as the emergence of large language models, exhibiting unprecedented ability in few-shot generalization, scalability, and task generality, which is however absent in time series models.
RIDERS: Radar-Infrared Depth Estimation for Robust Sensing
Dense depth recovery is crucial in autonomous driving, serving as a foundational element for obstacle avoidance, 3D object detection, and local path planning.
Parameter-Efficient Conversational Recommender System as a Language Processing Task
Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation.
Distilling Mathematical Reasoning Capabilities into Small Language Models
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability.
Self-supervised Event-based Monocular Depth Estimation using Cross-modal Consistency
In this paper, to lower the annotation cost, we propose a self-supervised event-based monocular depth estimation framework named EMoDepth.
A Novel Prompt-tuning Method: Incorporating Scenario-specific Concepts into a Verbalizer
The verbalizer, which serves to map label words to class labels, is an essential component of prompt-tuning.
RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale
To circumvent this issue, we learn to augment versatile and robust monocular depth prediction with the dense metric scale induced from sparse and noisy Radar data.
FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning
When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge.
Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible.
1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation
The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance.
A Generalist FaceX via Learning Unified Facial Representation
This work presents FaceX framework, a novel facial generalist model capable of handling diverse facial tasks simultaneously.
Learnable Chamfer Distance for Point Cloud Reconstruction
As point clouds are 3D signals with permutation invariance, most existing works train their reconstruction networks by measuring shape differences with the average point-to-point distance between point clouds matched with predefined rules.
Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models
This paper presents Paint3D, a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs.
Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem.
VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering
By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair.
CR-SFP: Learning Consistent Representation for Soft Filter Pruning
In this paper, we propose to mitigate this gap by learning consistent representation for soft filter pruning, dubbed as CR-SFP.
Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
Following this spirit, this paper explores plain ViT architecture for MUAD.
MaxQ: Multi-Axis Query for N:M Sparsity Network
Meanwhile, a sparsity strategy that gradually increases the percentage of N:M weight blocks is applied, which allows the network to heal from the pruning-induced damage progressively.
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving.
ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network
Graph Comparative Learning (GCL) is a self-supervised method that combines the advantages of Graph Convolutional Networks (GCNs) and comparative learning, making it promising for learning node representations.
Towards Knowledge-driven Autonomous Driving
This paper explores the emerging knowledge-driven autonomous driving technologies.
Open-Vocabulary Segmentation with Semantic-Assisted Calibration
We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction.
Universal Segmentation at Arbitrary Granularity with Language Instruction
This paper aims to achieve universal segmentation of arbitrary semantic level.
Ranked #1 on
Referring Expression Segmentation
on RefCOCOg-test
(using extra training data)
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis.
Ranked #1 on
Highlight Detection
on YouTube Highlights
Information-Theoretic Generalization Bounds for Transductive Learning and its Applications
In this paper, we develop data-dependent and algorithm-dependent generalization bounds for transductive learning algorithms in the context of information theory for the first time.
APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation
To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection
Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) paradigm.
VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification
VIGraph strictly adheres to the concept of imbalance when constructing imbalanced graphs and innovatively leverages the variational inference (VI) ability of Variational GAE to generate nodes for minority classes.
CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects.
LLMs may Dominate Information Access: Neural Retrievers are Biased Towards LLM-Generated Texts
We refer to this category of biases in neural retrieval models towards the LLM-generated text as the \textbf{source bias}.
ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair
With the growing interest on Large Language Models (LLMs) for fault localization and program repair, ensuring the integrity and generalizability of the LLM-based methods becomes paramount.
Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning
Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task.
Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method
Thus, we propose GraphRank, a simple yet efficient graph contrastive learning method that addresses the problem of false negative samples by redefining the concept of negative samples to a certain extent, thereby avoiding the issue of false negative samples.
In-context Learning with Transformer Is Really Equivalent to a Contrastive Learning Pattern
To the best of our knowledge, our work is the first to provide the understanding of ICL from the perspective of contrastive learning and has the potential to facilitate future model design by referring to related works on contrastive learning.
A Surrogate-Assisted Extended Generative Adversarial Network for Parameter Optimization in Free-Form Metasurface Design
Metasurfaces have widespread applications in fifth-generation (5G) microwave communication.
HGCVAE: Integrating Generative and Contrastive Learning for Heterogeneous Graph Learning
In this study, we aim to explore the problem of generative SSL in the context of heterogeneous graph learning (HGL).
Understanding Fairness Surrogate Functions in Algorithmic Fairness
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
Experimental quantum natural gradient optimization in photonics
Our work opens up a vista of utilizing QNG in photonics to implement practical near-term quantum applications.
SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration
To overcome them, this paper proposes a novel \emph{\textbf{S}oft \textbf{U}niform \textbf{B}lock \textbf{P}runing} (SUBP) approach to train a uniform 1$\times$N sparse structured network from scratch.
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series, with each token formed by multiple variates of the same timestamp.
Sentence-level Prompts Benefit Composed Image Retrieval
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption.
Ranked #1 on
Image Retrieval
on CIRR
Perfect Alignment May be Poisonous to Graph Contrastive Learning
Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones.
Quantum generative adversarial learning in photonics
Quantum Generative Adversarial Networks (QGANs), an intersection of quantum computing and machine learning, have attracted widespread attention due to their potential advantages over classical analogs.
Can the Query-based Object Detector Be Designed with Fewer Stages?
Query-based object detectors have made significant advancements since the publication of DETR.
Real3D-AD: A Dataset of Point Cloud Anomaly Detection
High-precision point cloud anomaly detection is the gold standard for identifying the defects of advancing machining and precision manufacturing.
Predicting Fatigue Crack Growth via Path Slicing and Re-Weighting
Predicting potential risks associated with the fatigue of key structural components is crucial in engineering design.
A Comprehensive Survey on Deep Learning Techniques in Educational Data Mining
With the increasing complexity and diversity of educational data, Deep Learning techniques have shown significant advantages in addressing the challenges associated with analyzing and modeling this data.
Object Detection for Caries or Pit and Fissure Sealing Requirement in Children's First Permanent Molars
The best result for YOLOXs model with tiling strategy is 72. 3 mAP. 5, while the best result without tiling strategy is 71. 2.
IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
Adaptive Multi-Modalities Fusion in Sequential Recommendation Systems
We propose a graph-based approach (named MMSR) to fuse modality features in an adaptive order, enabling each modality to prioritize either its inherent sequential nature or its interplay with other modalities.
Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentation
In this paper, we present a novel semi-supervised framework for visual BEV semantic segmentation to boost performance by exploiting unlabeled images during the training.
Autonomous Vehicles
Bird's-Eye View Semantic Segmentation
+2
Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking
In this paper, we forsake the conventional Siamese paradigm and propose a novel single-branch framework, SyncTrack, synchronizing the feature extracting and matching to avoid forwarding encoder twice for template and search region as well as introducing extra parameters of matching network.
DISCO: Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
Large-scale well-annotated datasets are of great importance for training an effective object detector.
Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold.
Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
Class prototype construction and matching are core aspects of few-shot action recognition.
End-to-End Beam Retrieval for Multi-Hop Question Answering
This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops.
Ranked #1 on
Question Answering
on HotpotQA
A Survey on Model Compression for Large Language Models
As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations.
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning
Therefore, a few data-free methods are proposed to address this problem, but they perform data-free pruning and quantization separately, which does not explore the complementarity of pruning and quantization.
Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning
In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT).
Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution
Since the high resolution of intermediate features in SISR models increases memory and computational requirements, efficient SISR transformers are more favored.
Unsupervised Representation Learning for Time Series: A Review
However, there is a lack of systematic analysis of unsupervised representation learning approaches for time series.
Multimodal Adaptation of CLIP for Few-Shot Action Recognition
The adapters we design can combine information from video-text multimodal sources for task-oriented spatiotemporal modeling, which is fast, efficient, and has low training costs.
High Probability Analysis for Non-Convex Stochastic Optimization with Clipping
Gradient clipping is a commonly used technique to stabilize the training process of neural networks.
Can Large Language Models Empower Molecular Property Prediction?
Molecular property prediction has gained significant attention due to its transformative potential in multiple scientific disciplines.
YOLIC: An Efficient Method for Object Localization and Classification on Edge Devices
In the realm of Tiny AI, we introduce ``You Only Look at Interested Cells" (YOLIC), an efficient method for object localization and classification on edge devices.
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
In this paper, we propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process.
PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation
Firstly, we propose a non-learning Sparse Instance Proposal (SIP) module with the ``sampling-shifting-grouping" scheme to directly group thing points into instances from the raw point cloud efficiently.
SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion
However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration.
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
To fill this gap, we review current state-of-the-art SSL methods for time series data in this article.
How Can Recommender Systems Benefit from Large Language Models: A Survey
In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems.
ViG-UNet: Vision Graph Neural Networks for Medical Image Segmentation
Deep neural networks have been widely used in medical image analysis and medical image segmentation is one of the most important tasks.
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics.
SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment.
Ranked #2 on
Referring Expression Segmentation
on A2D Sentences
(using extra training data)
Learning Global-aware Kernel for Image Harmonization
To address this issue, we propose a novel Global-aware Kernel Network (GKNet) to harmonize local regions with comprehensive consideration of long-distance background references.
Ranked #5 on
Image Harmonization
on iHarmony4
Correlation Pyramid Network for 3D Single Object Tracking
Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features.
Towards Understanding the Generalization of Graph Neural Networks
After that, we provide high probability bounds of generalization gap for popular GNNs.
FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume
Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces.
Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator
More specifically, given a textured face as the source and the rendered face projected from the desired 3DMM coefficients as the target, our proposed Texture-Geometry-aware Diffusion Model decomposes the complex transfer problem into multi-conditional denoising process, where a Texture Attention-based module accurately models the correspondences between appearance and geometry cues contained in source and target conditions, and incorporate extra implicit information for high-fidelity talking face generation.
High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning
Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space, which inherits rich semantic prior from CLIP.
NeRF-Loc: Visual Localization with Conditional Neural Radiance Field
We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer.
RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification
Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies.
Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant.
Robust Neural Architecture Search
Neural Architectures Search (NAS) becomes more and more popular over these years.
Learning Federated Visual Prompt in Null Space for MRI Reconstruction
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy.
Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
Our TWEU employs an evidential deep layer to produce the uncertainty score with the DR staging results for client reliability evaluation.
Global Knowledge Calibration for Fast Open-Vocabulary Segmentation
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS).
Knowledge Distillation
Open Vocabulary Semantic Segmentation
+4
RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction
Recently, neural implicit surfaces have become popular for multi-view reconstruction.
Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo).
OverlapNetVLAD: A Coarse-to-Fine Framework for LiDAR-based Place Recognition
Place recognition is a challenging yet crucial task in robotics.
A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation
For overlap detection, a cross-attention module is applied for interacting contextual information of input point clouds, followed by a classification head to estimate the overlapping region.
TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation
One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention.
Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK
High-order Takagi-Sugeno-Kang (TSK) fuzzy classifiers possess powerful classification performance yet have fewer fuzzy rules, but always be impaired by its exponential growth training time and poorer interpretability owing to High-order polynomial used in consequent part of fuzzy rule, while Low-order TSK fuzzy classifiers run quickly with high interpretability, however they usually require more fuzzy rules and perform relatively not very well.
Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning
We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios.
Operation-level Progressive Differentiable Architecture Search
It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.
Improving Differentiable Architecture Search via Self-Distillation
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.
Learning Discretized Neural Networks under Ricci Flow
By introducing a partial differential equation on metrics, i. e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the $L^2$-norm perturbation.
History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.
IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing
We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications.
Reliable Federated Disentangling Network for Non-IID Domain Feature
To the best of our knowledge, our proposed RFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features.
FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation
The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods.
Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition
In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner.
BSNet: Lane Detection via Draw B-spline Curves Nearby
The locality of lane representation is the ability to modify lanes locally which can simplify parameter optimization.
Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation
In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework.
RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space
Specifically, we use the contrastive constraint to help CALoss learn a representation space with shape similarity, while we introduce the adversarial strategy to help CALoss mine differences between reconstructed results and ground truths.
HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search
To address these issues, we propose a hierarchical optimal transport metric called HOTNN for measuring the similarity of different networks.
Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training
We randomly initialize a dense neural network and find appropriate binary masks for the weights to obtain fair sparse subnetworks without any weight training.
Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning
Federated learning has gained recognitions as a secure approach for safeguarding local private data in collaborative learning.
Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty
DEviS not only enhances the calibration and robustness of baseline segmentation accuracy but also provides high-efficiency uncertainty estimation for reliable predictions.
A Survey on Federated Recommendation Systems
Federated learning has recently been applied to recommendation systems to protect user privacy.
Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition
Then in the visual flow, visual prototypes are computed by a Temporal-Relational CrossTransformer (TRX) module for example.
AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer
Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair.
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting.
Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images
Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed.
Inductive Graph Transformer for Delivery Time Estimation
Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences.
Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals
Edge caching plays an increasingly important role in boosting user content retrieval performance while reducing redundant network traffic.
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.
Generative Model Watermarking Based on Human Visual System
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
Mask-Guided Image Person Removal with Data Synthesis
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains.
Localizing Anatomical Landmarks in Ocular Images using Zoom-In Attentive Networks
Therefore, localization has its unique challenges different from segmentation or detection.
Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.
Exemplar-Based Image Colorization with A Learning Framework
This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image.
Scatter Points in Space: 3D Detection from Multi-view Monocular Images
3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision.
Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging.
Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective
However, there still lack efforts to evaluate the robustness of such CF systems in deployment.
ATPL: Mutually enhanced adversarial training and pseudo labeling for unsupervised domain adaptation
Accordingly, ATPL will use the pseudo-labeled information to improve the adversarial training process, which can guarantee the feature transferability by generating adversarial data to fill in the domain gap.
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
DA$^2$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping
In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects.
Layer-refined Graph Convolutional Networks for Recommendation
Specifically, these models usually aggregate all layer embeddings for node updating and achieve their best recommendation performance within a few layers because of over-smoothing.
Adaptive Assignment for Geometry Aware Local Feature Matching
The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance.
E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context
However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance.
Ranked #4 on
Video Reconstruction
on UVG
Learning Quality-aware Dynamic Memory for Video Object Segmentation
However, they mainly focus on better matching between the current frame and the memory frames without explicitly paying attention to the quality of the memory.
Ranked #11 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
(using extra training data)
Bootstrap Latent Representations for Multi-modal Recommendation
Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e. g., user-user or item-item relation graph) to augment the learned representations of users and/or items.
Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.
EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.
Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
Enhancing Sequential Recommendation with Graph Contrastive Learning
Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.
Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.
UniInst: Unique Representation for End-to-End Instance Segmentation
Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e. g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions.
Ridgeless Regression with Random Features
Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.
Understanding the Generalization Performance of Spectral Clustering Algorithms
The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance.
Sharper Utility Bounds for Differentially Private Models
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
Stability and Generalization of Differentially Private Minimax Problems
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images.
Ranked #9 on
Optical Flow Estimation
on KITTI 2015 (train)
Region-Aware Face Swapping
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction.
Towards Efficient and Scalable Sharpness-Aware Minimization
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers.
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance.
Ranked #39 on
Anomaly Detection
on MVTec AD
Guide Local Feature Matching by Overlap Estimation
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important.
A Survey of Visual Sensory Anomaly Detection
In this survey, we are the first one to provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.
Lightweight Object-level Topological Semantic Mapping and Long-term Global Localization based on Graph Matching
In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness.
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.
Deep Domain Adversarial Adaptation for Photon-efficient Imaging
Photon-efficient imaging with the single-photon light detection and ranging (LiDAR) captures the three-dimensional (3D) structure of a scene by only a few detected signal photons per pixel.
Robust photon-efficient imaging using a pixel-wise residual shrinkage network
Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios.
Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase
However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views.
Dynamically Stable Poincaré Embeddings for Neural Manifolds
As a result, we prove that, if initial metrics have an $L^2$-norm perturbation which deviates from the Hyperbolic metric on the Poincar\'e ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric.
SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Network
To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild.
Searching Parameterized AP Loss for Object Detection
In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
MSP : Refine Boundary Segmentation via Multiscale Superpixel
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
Refined Learning Bounds for Kernel and Approximate $k$-Means
In this paper, we study the statistical properties of kernel $k$-means and Nystr\"{o}m-based kernel $k$-means, and obtain optimal clustering risk bounds, which improve the existing risk bounds.
Towards Sharper Generalization Bounds for Structured Prediction
In the smoothness scenario, we provide generalization bounds that are not only a logarithmic dependency on the label set cardinality but a faster convergence rate of order $\mathcal{O}(\frac{1}{n})$ on the sample size $n$.
Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation
In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation.
Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN
In this work, a novel Multidirectional Perception Generative Adversarial Network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages.
MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation
Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions.
Ranked #1 on
Referring Expression Segmentation
on G-Ref test B
Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application
Benefiting from the strong ability of the pre-trained model, the research on Chinese Word Segmentation (CWS) has made great progress in recent years.
Thoughts on the Consistency between Ricci Flow and Neural Network Behavior
During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.
A layer-stress learning framework universally augments deep neural network tasks
Here we presented a layer-stress deep learning framework (x-NN) which implemented automatic and wise depth decision on shallow or deep feature map in a deep network through firstly designing enough number of layers and then trading off them by Multi-Head Attention Block.
Learning Rates for Nonconvex Pairwise Learning
We first successfully establish learning rates for these algorithms in a general nonconvex setting, where the analysis sheds insights on the trade-off between optimization and generalization and the role of early-stopping.
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation
Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary.
Ranked #3 on
Instance Segmentation
on LVIS v1.0 val
Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking
Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions.
