Search Results for author:
Found 60 papers, 17 papers with code
Fast Segment Anything
In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
Ranked #4 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks.
DPT: Deformable Patch-based Transformer for Visual Recognition
To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches.
Ranked #17 on
Semantic Segmentation
on DensePASS
Identity-Guided Human Semantic Parsing for Person Re-Identification
In this paper, we propose the identity-guided human semantic parsing approach (ISP) to locate both the human body parts and personal belongings at pixel-level for aligned person re-ID only with person identity labels.
Ranked #40 on
Person Re-Identification
on DukeMTMC-reID
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.
Adaptive Class Suppression Loss for Long-Tail Object Detection
To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies.
Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models
More importantly, we present $\textbf{Griffon}$, a purely LVLM-based baseline, which does not require the introduction of any special tokens, expert models, or additional detection modules.
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpass the performance of task-specific experts in complex and dense scenarios.
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
PASS learns to match the output of the local views and global views on the same [PART].
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.
Multi-objective Deep Reinforcement Learning for Mobile Edge Computing
In this study, we address this issue by formulating a multi-objective offloading problem for MEC with multiple edges to minimize expected long-term energy consumption and transmission delay while considering unknown preferences as parameters.
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.
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Retraining-free is important for LLMs' pruning methods.
Task Decoupled Knowledge Distillation For Lightweight Face Detectors
This method decouples the distillation task of face detection into two subtasks, i. e., the classification distillation subtask and the regression distillation subtask.
Pruning-aware Sparse Regularization for Network Pruning
MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model.
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks.
A Quantitative Analytical Model for Predicting and Optimizing the Rate Performance of Battery Cells
An important objective of designing lithium-ion rechargeable battery cells is to maximize their rate performance without compromising the energy density, which is mainly achieved through computationally expensive numerical simulations at present.
Materials Science Applied Physics
High-speed Tracking with Multi-kernel Correlation Filters
In this paper, we will introduce the MKL into KCF in a different way than MKCF.
Fast Kernelized Correlation Filters without Boundary Effect
To achieve the fast training and detection, a set of cyclic bases is introduced to construct the filter.
PCN: Part and Context Information for Pedestrian Detection with CNNs
To take advantage of the body parts and context information for pedestrian detection, we propose the part and context network (PCN) in this work.
On the Relations of Correlation Filter Based Trackers and Struck
In recent years, two types of trackers, namely correlation filter based tracker (CF tracker) and structured output tracker (Struck), have exhibited the state-of-the-art performance.
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes.
Multi-Kernel Correlation Filter for Visual Tracking
In this paper, we will derive a multi-kernel correlation filter (MKCF) based tracker which fully takes advantage of the invariance-discriminative power spectrums of various features to further improve the performance.
Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.
Ranked #1 on
Face Alignment
on 300W
(NME_inter-pupil (%, Full) metric)
Learning Feature Embeddings for Discriminant Model based Tracking
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.
Repositioning Bikes with Carrier Vehicles and Bike Trailers in Bike Sharing Systems
Bike Sharing Systems (BSSs) have been adopted in many major cities of the world due to traffic congestion and carbon emissions.
Large Batch Optimization for Object Detection: Training COCO in 12 Minutes
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.
Adaptive Variance Based Label Distribution Learning For Facial Age Estimation
Some existing methods adopt distribution learning to tackle this issue by exploiting the semantic correlation between age labels.
Ranked #6 on
Age Estimation
on MORPH album2 (Caucasian)
Blended Grammar Network for Human Parsing
Although human parsing has made great progress, it still faces a challenge, i. e., how to extract the whole foreground from similar or cluttered scenes effectively.
Improving the spatial resolution of a BOTDA sensor using deconvolution algorithm
The frequency dependency of Brillouin gain temporal envelope is investigated by simulation, and its impact on the recovered results of deconvolution algorithm is thoroughly analyzed.
Identify Influential Spreaders in Asymmetrically Interacting Multiplex Networks
Our work provides insights on the importance of nodes in the multiplex network and gives a feasible framework to investigate influential spreaders in the asymmetrically coevolving dynamics.
Physics and Society
AAformer: Auto-Aligned Transformer for Person Re-Identification
In this paper, we introduce an alignment scheme in Transformer architecture for the first time and propose the Auto-Aligned Transformer (AAformer) to automatically locate both the human parts and non-human ones at patch-level.
MST: Masked Self-Supervised Transformer for Visual Representation
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
Improving Multiple Object Tracking With Single Object Tracking
Despite considerable similarities between multiple object tracking (MOT) and single object tracking (SOT) tasks, modern MOT methods have not benefited from the development of SOT ones to achieve satisfactory performance.
Enabling variable high spatial resolution retrieval from a long pulse BOTDA sensor
We propose a convolutional neural network (CNN) to process the data of conventional Brillouin optical time domain analysis (BOTDA) sensors, which achieves unprecedented performance improvement that allows to directly retrieve higher spatial resolution (SR) from the sensing system that use long pump pulses.
High-Performance Discriminative Tracking With Transformers
End-to-end discriminative trackers improve the state of the art significantly, yet the improvement in robustness and efficiency is restricted by the conventional discriminative model, i. e., least-squares based regression.
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism.
Ranked #64 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
Thermal Modelling and Controller Design of an Alkaline Electrolysis System under Dynamic Operating Conditions
A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design.
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
Beyond the Limitation of Pulse Width in Optical Time-domain Reflectometry
Here, we propose and experimentally demonstrate an OTDR deconvolution neural network based on deep convolutional neural networks.
C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection
The decision boundary between any two categories is the angular bisector of their weight vectors.
Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID).
Transfering Low-Frequency Features for Domain Adaptation
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision.
Design of the PID temperature controller for an alkaline electrolysis system with time delays
This paper focuses on the design of the PID temperature controller for an alkaline electrolysis system to achieve fast and stable temperature control.
Deep Learning for Human Parsing: A Survey
Human parsing is a key topic in image processing with many applications, such as surveillance analysis, human-robot interaction, person search, and clothing category classification, among many others.
Efficient Masked Autoencoders with Self-Consistency
However, its high random mask ratio would result in two serious problems: 1) the data are not efficiently exploited, which brings inefficient pre-training (\eg, 1600 epochs for MAE $vs.$ 300 epochs for the supervised), and 2) the high uncertainty and inconsistency of the pre-trained model, \ie, the prediction of the same patch may be inconsistent under different mask rounds.
FreConv: Frequency Branch-and-Integration Convolutional Networks
In the high-frequency branch, a derivative-filter-like architecture is designed to extract the high-frequency information while a light extractor is employed in the low-frequency branch because the low-frequency information is usually redundant.
Real-time FPGA Implementation of CNN-based Distributed Fiber Optic Vibration Event Recognition Method
Utilizing optical fibers to detect and pinpoint vibrations, Distributed Optical Fiber Vibration Sensing (DVS) technology provides real-time monitoring and surveillance of wide-reaching areas.
When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation
SplitFed learning (SFL) is a recent distributed approach that alleviates computation workload at the client device by splitting the model at a cut layer into two parts, where clients only need to train part of the model.
FrFT based estimation of linear and nonlinear impairments using Vision Transformer
To comprehensively assess optical fiber communication system conditions, it is essential to implement joint estimation of the following four critical impairments: nonlinear signal-to-noise ratio (SNRNL), optical signal-to-noise ratio (OSNR), chromatic dispersion (CD) and differential group delay (DGD).
EFFL: Egalitarian Fairness in Federated Learning for Mitigating Matthew Effect
Recent advances in federated learning (FL) enable collaborative training of machine learning (ML) models from large-scale and widely dispersed clients while protecting their privacy.
Price of Stability in Quality-Aware Federated Learning
The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising.
Continual Instruction Tuning for Large Multimodal Models
2) Are the existing three classes of continual learning methods still applicable to the continual instruction tuning of LMMs?
Mitigating Hallucination in Visual Language Models with Visual Supervision
Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally.
Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
The uncertain edge load dynamics, the nature of the fractional objective, and hybrid continuous-discrete action space (due to the joint optimization) make this problem challenging and existing approaches not directly applicable.
Convergence Analysis of Split Federated Learning on Heterogeneous Data
We further extend the analysis to non-convex objectives and where some clients may be unavailable during training.
BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
Blind face restoration is a challenging task due to the unknown and complex degradation.
Efficient Online Unlearning via Hessian-Free Recollection of Individual Data Statistics
In this work, we propose a Hessian-free online unlearning method.
PraFFL: A Preference-Aware Scheme in Fair Federated Learning
Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model for any special group (e. g., male or female) of sensitive features.
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories.
