Search Results for author:
Found 25 papers, 9 papers with code
Interpreting Object-level Foundation Models via Visual Precision Search
Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection.
Few-Shot Open-Set Object Detection via Conditional Evidence Decoupling
To mitigate this issue, we develop a two-stage open-set object detection framework with prompt learning, which delves into conditional evidence decoupling for the unknown rejection.
MM-GTUNets: Unified Multi-Modal Graph Deep Learning for Brain Disorders Prediction
Graph deep learning (GDL) has demonstrated impressive performance in predicting population-based brain disorders (BDs) through the integration of both imaging and non-imaging data.
A Novel Approach to Evaluating Battery Charger Controller Design with Nonlinear PID Controller in an Extendable CHIL Setup
The design and development of power electronics converters pose a multitude of challenges.
Design and Analysis of a Detuned Series-Series IPT System with Solenoid Coil Structure for Drone Charging Applications
This paper proposes a new coil configuration that uses solenoid ferrites on the receiver side instead of planar ferrite coils that are employed in existing wireless charging systems. The solenoid ferrites are used in the drone legs to help mount the receiver on a moving truck while the two parts of the transmitter are placed on the truck. To validate this idea a detuned transmitter series-series (SS) compensated IPT prototype system has been investigated to charge the onboard battery of a drone. The proposed detuned design helps to limit the system output power and transmitter side current at even zero coupling condition and tolerates misalignment positions.
Gallium Nitride (GaN) based High-Power Multilevel H-Bridge Inverter for Wireless Power Transfer of Electric Vehicles
This paper details the system specifications for the wireless charging of EVs, providing theoretical analysis and a control strategy for the modular design of a 75-kW 3-level and 4-level Hbridge inverter.
Less is More: Fewer Interpretable Region via Submodular Subset Selection
For incorrectly predicted samples, our method achieves gains of 81. 0% and 18. 4% compared to the HSIC-Attribution algorithm in the average highest confidence and Insertion score respectively.
Ranked #1 on
Error Understanding
on CUB-200-2011
Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition.
Fair Text-to-Image Diffusion via Fair Mapping
In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions.
ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understanding
It usually includes slot filling and intent detection (SFID) tasks aiming at semantic parsing of utterances.
Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection
Concretely, the identity hider benefits from two specially designed modules: 1) The virtual face generation module generates a virtual face with a new appearance by manipulating the latent space of StyleGAN2.
Privacy-Enhancing Face Obfuscation Guided by Semantic-Aware Attribution Maps
Within this module, we introduce a pixel importance estimation model based on Shapley value to obtain a pixel-level attribution map, and then each pixel on the attribution map is aggregated into semantic facial parts, which are used to quantify the importance of different facial parts.
A GOA-Based Fault-Tolerant Trajectory Tracking Control for an Underwater Vehicle of Multi-Thruster System without Actuator Saturation
This paper proposes an intelligent fault-tolerant control (FTC) strategy to tackle the trajectory tracking problem of an underwater vehicle (UV) under thruster damage (power loss) cases and meanwhile resolve the actuator saturation brought by the vehicle's physical constraints.
Towards Generalized Few-Shot Open-Set Object Detection
In this paper, we seek a solution for the generalized few-shot open-set object detection (G-FOOD), which aims to avoid detecting unknown classes as known classes with a high confidence score while maintaining the performance of few-shot detection.
Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual Explanations
Different from existing models, in this paper, we propose a new interpretation method that explains the image similarity models by salience maps and attribute words.
Progressive Contour Regression for Arbitrary-Shape Scene Text Detection
In the second stage, the contours of the oriented text proposals are iteratively regressed to arbitrarily shaped ones.
Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition
To establish an effective features extracting and classification model is still a challenging task.
Acquisition of Channel State Information for mmWave Massive MIMO: Traditional and Machine Learning-based Approaches
The accuracy of channel state information (CSI) acquisition directly affects the performance of millimeter wave (mmWave) communications.
Framework on Deep Learning Based Joint Hybrid Processing for mmWave Massive MIMO Systems
For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is essential to significantly reduce the complexity and cost but is quite challenging to be jointly optimized over the transmitter and receiver.
Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning
Vacant taxi drivers' passenger seeking process in a road network generates additional vehicle miles traveled, adding congestion and pollution into the road network and the environment.
Multi-Class Learning: From Theory to Algorithm
In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.
Local Shrunk Discriminant Analysis (LSDA)
Principal component analysis (PCA) is a traditional technique for unsupervised dimensionality reduction, which is often employed to seek a projection to best represent the data in a least-squares sense, but if the original data is nonlinear structure, the performance of PCA will quickly drop.
Cascade one-vs-rest detection network for fine-grained recognition without part annotations
To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories.
SketchNet: Sketch Classification With Web Images
In this study, we present a weakly supervised approach that discovers the discriminative structures of sketch images, given pairs of sketch images and web images.
Diversity-Induced Multi-View Subspace Clustering
In this paper, we focus on how to boost the multi-view clustering by exploring the complementary information among multi-view features.
