Search Results for author:
Found 91 papers, 35 papers with code
Masked Generative Distillation
The current distillation algorithm usually improves students' performance by imitating the output of the teacher.
Track Anything: Segment Anything Meets Videos
Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos.
Caption Anything: Interactive Image Description with Diverse Multimodal Controls
Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e. g.}$, looking at the specified regions or telling in a particular text style.
Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
The model consists of two modules.
CARLS: Cross-platform Asynchronous Representation Learning System
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms.
Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
Overall, our method can create lifelike avatars with dynamic, realistic and generalized appearances.
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups.
Changer: Feature Interaction is What You Need for Change Detection
To verify the effectiveness of MetaChanger, we propose two derived models, ChangerAD and ChangerEx with simple interaction strategies: Aggregation-Distribution (AD) and "exchange".
Ranked #3 on
Change Detection
on LEVIR-CD
Building change detection for remote sensing images
Change Detection
+1
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
Focal and Global Knowledge Distillation for Detectors
Global distillation rebuilds the relation between different pixels and transfers it from teachers to students, compensating for missing global information in focal distillation.
Ranked #1 on
Knowledge Distillation
on MS COCO
Siamese NestedUNet Networks for Change Detection of High Resolution Satellite Image
In this paper, we improve the semantic segmentation network UNet++ and propose a fully convolutional siamese network (Siam-NestedUNet) for change detection.
Change Detection
Change detection for remote sensing images
+2
Rethinking Knowledge Distillation via Cross-Entropy
Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).
ViTKD: Practical Guidelines for ViT feature knowledge distillation
In this paper, we explore the way of feature-based distillation for ViT.
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
We decompose the KD loss and find the non-target loss from it forces the student's non-target logits to match the teacher's, but the sum of the two non-target logits is different, preventing them from being identical.
AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture
Then given a monocular RGB video of this subject, our method integrates information from both the image observation and the avatar prior, and accordingly recon-structs high-fidelity 3D textured models with dynamic details regardless of the visibility.
MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing
Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence.
PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
To this end, we present PoseVocab, a novel pose encoding method that encourages the network to discover the optimal pose embeddings for learning the dynamic human appearance.
Generative Adversarial Active Learning for Unsupervised Outlier Detection
In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution.
ConTNet: Why not use convolution and transformer at the same time?
It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.
Class-Incremental Learning with Generative Classifiers
As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned and by using importance sampling to estimate the likelihoods p(x|y).
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter
Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC).
Optical Character Recognition
Optical Character Recognition (OCR)
+1
Forward Laplacian: A New Computational Framework for Neural Network-based Variational Monte Carlo
Neural network-based variational Monte Carlo (NN-VMC) has emerged as a promising cutting-edge technique of ab initio quantum chemistry.
RGBD Object Tracking: An In-depth Review
Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon.
Temporal Action Segmentation from Timestamp Supervision
To demonstrate the effectiveness of timestamp supervision, we propose an approach to train a segmentation model using only timestamps annotations.
Ranked #4 on
Weakly Supervised Action Localization
on GTEA
Salient Positions based Attention Network for Image Classification
Aimed at both questions this paper proposes the salient positions-based attention scheme SPANet, which is inspired by some interesting observations on the attention maps and affinity matrices generated in self-attention scheme.
Thoracic Disease Identification and Localization with Limited Supervision
Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning.
RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction
However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.
Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains.
Resource-Efficient RGBD Aerial Tracking
However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view.
Causality Analysis for Evaluating the Security of Large Language Models
Based on a layer-level causality analysis, we show that RLHF has the effect of overfitting a model to harmful prompts.
Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios.
Contrastive Learning
Multivariate Time Series Forecasting
+2
MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion
Multi-modality image fusion (MMIF) aims to integrate complementary information from different modalities into a single fused image to represent the imaging scene and facilitate downstream visual tasks comprehensively.
Inferring Inference
Given a time series of neural activity during a perceptual inference task, our framework finds (i) the neural representation of relevant latent variables, (ii) interactions between these variables that define the brain's internal model of the world, and (iii) message-functions specifying the inference algorithm.
EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.
An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space.
Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.
Learning Topics using Semantic Locality
The topic modeling discovers the latent topic probability of the given text documents.
Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations.
Image Dataset for Visual Objects Classification in 3D Printing
The rapid development in additive manufacturing (AM), also known as 3D printing, has brought about potential risk and security issues along with significant benefits.
C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
It is of vital importance to enable 3D printers to identify the objects to be printed, so that the manufacturing procedure of an illegal weapon can be terminated at the early stage.
C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.
A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
In the first prediction part, we focus on predicting the downward trend, which is an earlier stage of the customer lifecycle compared to churn.
Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia.
An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost.
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.
A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer
In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization.
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.
SEP-Nets: Small and Effective Pattern Networks
By doing this, we show that previous deep CNNs such as GoogLeNet and Inception-type Nets can be compressed dramatically with marginal drop in performance.
Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
Recently, Deep Convolutional Neural Networks (DCNNs) have made unprecedented progress, achieving the accuracy close to, or even better than human-level perception in various tasks.
SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing
Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.
Improved Dropout for Shallow and Deep Learning
To exhibit the optimal dropout probabilities, we analyze the shallow learning with multinomial dropout and establish the risk bound for stochastic optimization.
Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization
This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov's accelerated gradient method.
A Unified Analysis of Stochastic Momentum Methods for Deep Learning
However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored.
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization
Negative curvature descent (NCD) method has been utilized to design deterministic or stochastic algorithms for non-convex optimization aiming at finding second-order stationary points or local minima.
CircConv: A Structured Convolution with Low Complexity
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.
Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention.
Learning From Brains How to Regularize Machines
We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity.
Long Short-Term Sample Distillation
The long-term teacher draws on snapshots from several epochs ago in order to provide steadfast guidance and to guarantee teacher--student differences, while the short-term one yields more up-to-date cues with the goal of enabling higher-quality updates.
RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
To address these issues, we focus on semi-supervised outlier detection with few identified anomalies, in the hope of using limited labels to achieve high detection accuracy.
Robust 3D Self-portraits in Seconds
In this paper, we propose an efficient method for robust 3D self-portraits using a single RGBD camera.
E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Joint Multi-Dimension Pruning via Numerical Gradient Update
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition.
POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture
By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions.
Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras
Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance.
Ranked #2 on
3D Multi-Person Pose Estimation
on Shelf
The emergence of cooperation from shared goals in the Systemic Sustainability Game of common pool resources
The sustainable use of common-pool resources (CPRs) is a major environmental governance challenge because of their possible over-exploitation.
Low-Resource Text Classification via Cross-lingual Language Model Fine-tuning
There are major challenges of low-resource agglutinative text classification the lack of labeled data in a target domain and morphologic diversity of derivations in language structures.
VRConvMF: Visual Recurrent Convolutional Matrix Factorization for Movie Recommendation
Fortunately, context-aware recommender systems can alleviate the sparsity problem by making use of some auxiliary information, such as the information of both the users and items.
Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Context-Aware Movie Recommendation
As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data.
Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks
In this work we trained graph neural networks to fit time series from an example nonlinear dynamical system, the belief propagation algorithm.
SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text
Specifically, we propose a style bank to parameterize the specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles.
MSCET: A Multi-Scenario Offloading Schedule for Biomedical Data Processing and Analysis in Cloud-Edge-Terminal Collaborative Vehicular Networks
The vehicles can offload the computation intensive tasks to the cloud to save the resource of edge.
Prompting for Multi-Modal Tracking
Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking.
Ranked #12 on
Rgb-T Tracking
on LasHeR
Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction
To improve the discriminative ability of the loss function, we incorporate a margin into the contrastive learning.
Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning.
Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored.
Balancing Privacy Protection and Interpretability in Federated Learning
Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information.
A Graph Reconstruction by Dynamic Signal Coefficient for Fault Classification
To improve the performance in identifying the faults under strong noise for rotating machinery, this paper presents a dynamic feature reconstruction signal graph method, which plays the key role of the proposed end-to-end fault diagnosis model.
Whole Slide Multiple Instance Learning for Predicting Axillary Lymph Node Metastasis
Breast cancer is a major concern for women's health globally, with axillary lymph node (ALN) metastasis identification being critical for prognosis evaluation and treatment guidance.
General Point Model with Autoencoding and Autoregressive
This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks.
A Wi-Fi Signal-Based Human Activity Recognition Using High-Dimensional Factor Models
As a consequence, the accuracy of human activity recognition based on Wi-Fi signals is compromised.
Robust Learning Based Condition Diagnosis Method for Distribution Network Switchgear
This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users.
Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs
However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature.
DCS-Net: Pioneering Leakage-Free Point Cloud Pretraining Framework with Global Insights
Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.
MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning.
RISAR: RIS-assisted Human Activity Recognition with Commercial Wi-Fi Devices
Human activity recognition (HAR) holds significant importance in smart homes, security, and healthcare.
Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling
To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information.
TexVocab: Texture Vocabulary-conditioned Human Avatars
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation.
Automatic Knowledge Graph Construction for Judicial Cases
Building on these results, we detail the automatic construction process of case knowledge graphs for judicial cases, enabling the assembly of knowledge graphs for hundreds of thousands of judgments.
