Search Results for author:
Found 39 papers, 13 papers with code
Defect Detection in Tire X-Ray Images: Conventional Methods Meet Deep Structures
This paper introduces a robust approach for automated defect detection in tire X-ray images by harnessing traditional feature extraction methods such as Local Binary Pattern (LBP) and Gray Level Co-Occurrence Matrix (GLCM) features, as well as Fourier and Wavelet-based features, complemented by advanced machine learning techniques.
Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing
Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images.
Neural Symbolic Regression using Control Variables
Experimental results demonstrate that the proposed SRCV significantly outperforms state-of-the-art baselines in discovering mathematical expressions with multiple variables.
CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
Our proposed method uses a center-based radar-camera fusion algorithm for object detection and utilizes a greedy algorithm for object association.
Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids
False data injection attacks (FDIAs) pose a significant security threat to power system state estimation.
CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection
In this paper, we focus on the problem of radar and camera sensor fusion and propose a middle-fusion approach to exploit both radar and camera data for 3D object detection.
Ranked #9 on
3D Object Detection
on nuscenes Camera-Radar
Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles
Our radar object proposal network uses radar point clouds to generate 3D proposals from a set of 3D prior boxes.
Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification
Transfer learning-based methods address this problem by pre-training in the source domain and fine-tuning on the target domain.
General Classification
Hyperspectral Image Classification
+1
Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery
Although inherently a classification problem, both representative and discriminative aspects of data need to be exploited in order to better distinguish unknown classes from known.
Unsupervised Pansharpening Based on Self-Attention Mechanism
First, the self-attention mechanism is proposed where the spatial varying detail extraction and injection functions are estimated according to the attention representations indicating spectral characteristics of the MSI with sub-pixel accuracy.
ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
We study the potential vulnerabilities of ML applied in CPSs by proposing Constrained Adversarial Machine Learning (ConAML), which generates adversarial examples that satisfy the intrinsic constraints of the physical systems.
Context Aware Road-user Importance Estimation (iCARE)
In this paper, we propose a novel architecture for road-user importance estimation which takes advantage of the local and global context of the scene.
advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
The results demonstrate that deep re-ID systems are vulnerable to our physical attacks.
Non-Local Representation based Mutual Affine-Transfer Network for Photorealistic Stylization
Photorealistic stylization aims to transfer the style of a reference photo onto a content photo in a natural fashion, such that the stylized image looks like a real photo taken by a camera.
Investigating Channel Pruning through Structural Redundancy Reduction -- A Statistical Study
Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning.
RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles
Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image.
Ranked #1 on
3D Object Detection
on nuScenes-F
Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net
With this design, the network allows to extract correlated spectral and spatial information from unregistered images that better preserves the spectral information.
Image Super-Resolution by Neural Texture Transfer
Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given.
Ranked #2 on
Image Super-Resolution
on CUFED5 - 4x upscaling
Speeding up convolutional networks pruning with coarse ranking
In specific, with the proposed method, 75% and 54% of the total computation time for the whole pruning procedure can be reduced for AlexNet on CIFAR-10, and for VGG-16 on ImageNet, respectively.
Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers
In this work, we propose a novel single-shot channel pruning approach based on alternating direction methods of multipliers (ADMM), which can eliminate the need for complex iterative pruning and fine-tuning procedure and achieve a target compression ratio with only one run of pruning and fine-tuning.
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.
Attention-based Few-Shot Person Re-identification Using Meta Learning
In this paper, we investigate the challenging task of person re-identification from a new perspective and propose an end-to-end attention-based architecture for few-shot re-identification through meta-learning.
Fast-converging Conditional Generative Adversarial Networks for Image Synthesis
Building on top of the success of generative adversarial networks (GANs), conditional GANs attempt to better direct the data generation process by conditioning with certain additional information.
Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
We refer to the proposed architecture as unsupervised Sparse Dirichlet-Net, or uSDN.
Talking Face Generation by Conditional Recurrent Adversarial Network
Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.
Reference-Conditioned Super-Resolution by Neural Texture Transfer
We focus on transferring the high-resolution texture from reference images to the super-resolution process without the constraint of content similarity between reference and target images, which is a key difference from previous example-based methods.
Discriminative Cross-View Binary Representation Learning
Learning compact representation is vital and challenging for large scale multimedia data.
Decoupled Learning for Conditional Adversarial Networks
Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks.
Person Re-identification Using Visual Attention
Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.
r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
A more generalized question is that if a large proportion (e. g., more than 50%) of the face/sketch is missing, can a realistic whole face sketch/image still be estimated.
Addressing Ambiguity in Multi-target Tracking by Hierarchical Strategy
We use a network flow approach to link detections in low-level and tracklets in high-level.
Multi-View Task-Driven Recognition in Visual Sensor Networks
Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications.
End-to-end Binary Representation Learning via Direct Binary Embedding
Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively.
Age Progression/Regression by Conditional Adversarial Autoencoder
In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator.
Feature Encoding in Band-limited Distributed Surveillance Systems
Distributed surveillance systems have become popular in recent years due to security concerns.
Derivative Delay Embedding: Online Modeling of Streaming Time Series
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
Group sparsity and geometry constrained dictionary learning for action recognition from depth maps.
Human action recognition based on the depth information provided by commodity depth sensors is an important yet challenging task.
Image color transfer to evoke different emotions based on color combinations
In this paper, a color transfer framework to evoke different emotions for images based on color combinations is proposed.
Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution
This is due to the unique property of the beta process model that the sparse representation can be decomposed to values and dictionary atom indicators.
