Search Results for author:
Found 98 papers, 55 papers with code
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
High-fidelity Endoscopic Image Synthesis by Utilizing Depth-guided Neural Surfaces
In surgical oncology, screening colonoscopy plays a pivotal role in providing diagnostic assistance, such as biopsy, and facilitating surgical navigation, particularly in polyp detection.
DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness
Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models.
Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Guidewire Segmentation in Robot-Assisted Cardiovascular Catheterization
Thus, we offer a less expensive method for real-time tool segmentation and tracking during robot-assisted cardiac catheterization.
Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy
We build CHM-Corr++, an interactive interface for CHM-Corr, enabling users to edit the feature importance map provided by CHM-Corr and observe updated model decisions.
Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model
The results reveal that Samba achieved unparalleled performance on commonly used remote sensing datasets for semantic segmentation.
On the Effectiveness of Heterogeneous Ensemble Methods for Re-identification
In this contribution, we introduce a novel ensemble method for the re-identification of industrial entities, using images of chipwood pallets and galvanized metal plates as dataset examples.
ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation
Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition.
Autonomous Catheterization with Open-source Simulator and Expert Trajectory
Endovascular robots have been actively developed in both academia and industry.
Leveraging Habitat Information for Fine-grained Bird Identification
Training CNNs and ViTs with habitat-augmented data results in an improvement of up to +0. 83 and +0. 23 points on NABirds and CUB-200, respectively.
WAVER: Writing-style Agnostic Text-Video Retrieval via Distilling Vision-Language Models Through Open-Vocabulary Knowledge
Text-video retrieval, a prominent sub-field within the domain of multimodal information retrieval, has witnessed remarkable growth in recent years.
TinyGSM: achieving >80% on GSM8k with small language models
Specifically for solving grade school math, the smallest model size so far required to break the 80\% barrier on the GSM8K benchmark remains to be 34B.
Ranked #58 on
Arithmetic Reasoning
on GSM8K
GlitchBench: Can large multimodal models detect video game glitches?
To address this gap, we introduce GlitchBench, a novel benchmark derived from video game quality assurance tasks, to test and evaluate the reasoning capabilities of LMMs.
Generating Valid and Natural Adversarial Examples with Large Language Models
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks.
Shape-Sensitive Loss for Catheter and Guidewire Segmentation
By computing the cosine similarity between these feature vectors, we gain a nuanced understanding of image similarity that goes beyond the limitations of traditional overlap-based measures.
3D Guidewire Shape Reconstruction from Monoplane Fluoroscopic Images
Endovascular navigation, essential for diagnosing and treating endovascular diseases, predominantly hinges on fluoroscopic images due to the constraints in sensory feedback.
Zero-Shot Medical Information Retrieval via Knowledge Graph Embedding
In the era of the Internet of Things (IoT), the retrieval of relevant medical information has become essential for efficient clinical decision-making.
Controllable Group Choreography using Contrastive Diffusion
Music-driven group choreography poses a considerable challenge but holds significant potential for a wide range of industrial applications.
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction.
Learning to Terminate in Object Navigation
This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods.
I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses
In the field of chest X-ray (CXR) diagnosis, existing works often focus solely on determining where a radiologist looks, typically through tasks such as detection, segmentation, or classification.
Grasp-Anything: Large-scale Grasp Dataset from Foundation Models
Foundation models such as ChatGPT have made significant strides in robotic tasks due to their universal representation of real-world domains.
Detecting the Sensing Area of A Laparoscopic Probe in Minimally Invasive Cancer Surgery
In surgical oncology, it is challenging for surgeons to identify lymph nodes and completely resect cancer even with pre-operative imaging systems like PET and CT, because of the lack of reliable intraoperative visualization tools.
HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation
Visual navigation, a foundational aspect of Embodied AI (E-AI), has been significantly studied in the past few years.
A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation
This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belonging to different centers.
Self-Supervised Learning for Point Clouds Data: A Survey
We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the pretexts' characteristics.
Translating Simulation Images to X-ray Images via Multi-Scale Semantic Matching
In this paper, we propose a new method to translate simulation images from an endovascular simulator to X-ray images.
Music-Driven Group Choreography
The proposed dataset consists of 16. 7 hours of paired music and 3D motion from in-the-wild videos, covering 7 dance styles and 16 music genres.
Style Transfer for 2D Talking Head Animation
In this paper, we present a new method to generate talking head animation with learnable style references.
Open-Vocabulary Affordance Detection in 3D Point Clouds
In this paper, we present the Open-Vocabulary Affordance Detection (OpenAD) method, which is capable of detecting an unbounded number of affordances in 3D point clouds.
A Light-weight Deep Learning Model for Remote Sensing Image Classification
In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image.
ViDeBERTa: A powerful pre-trained language model for Vietnamese
This paper presents ViDeBERTa, a new pre-trained monolingual language model for Vietnamese, with three versions - ViDeBERTa_xsmall, ViDeBERTa_base, and ViDeBERTa_large, which are pre-trained on a large-scale corpus of high-quality and diverse Vietnamese texts using DeBERTa architecture.
A Large-Scale Study of a Sleep Tracking and Improving Device with Closed-loop and Personalized Real-time Acoustic Stimulation
Various intervention therapies ranging from pharmaceutical to hi-tech tailored solutions have been available to treat difficulty in falling asleep commonly caused by insomnia in modern life.
SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation
Generating consistent and high-quality images from given texts is essential for visual-language understanding.
Uncertainty-aware Label Distribution Learning for Facial Expression Recognition
In this paper, we propose a new uncertainty-aware label distribution learning method to improve the robustness of deep models against uncertainty and ambiguity.
Facial Expression Recognition
Facial Expression Recognition (FER)
Inverse Image Frequency for Long-tailed Image Recognition
The long-tailed distribution is a common phenomenon in the real world.
Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency
Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system.
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations.
Long-tailed Instance Segmentation using Gumbel Optimized Loss
Major advancements have been made in the field of object detection and segmentation recently.
Ranked #11 on
Instance Segmentation
on LVIS v1.0 val
CodeT: Code Generation with Generated Tests
A natural way to evaluate the quality and correctness of a code solution is to run it against a set of test cases, but the manual creation of such test cases is often costly and time-consuming.
Ranked #1 on
Code Generation
on APPS
(Introductory Pass@1 metric)
Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology
In this paper, we present a new multigraph topology for cross-silo federated learning.
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase semantics given a context sentence or paragraph (instead of phrases alone).
How explainable are adversarially-robust CNNs?
Here, we perform the first, large-scale evaluation of the relations of the three criteria using 9 feature-importance methods and 12 ImageNet-trained CNNs that are of 3 training algorithms and 5 CNN architectures.
Fine-Grained Visual Classification using Self Assessment Classifier
We show that by effectively addressing the ambiguity in the top-k prediction classes, our method achieves new state-of-the-art results on CUB200-2011, Stanford Dog, and FGVC Aircraft datasets.
Ranked #4 on
Fine-Grained Image Classification
on Stanford Dogs
Understanding Public Opinion on Using Hydroxychloroquine for COVID-19 Treatment via Social Media
This paper studies the reactions of social network users on the recommendation of using HCQ for COVID-19 treatment by analyzing the reaction patterns and sentiment of the tweets.
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
Face identification (FI) is ubiquitous and drives many high-stake decisions made by law enforcement.
Global-Local Attention for Emotion Recognition
Our network is designed to extract features from both facial and context regions independently, then learn them together using the attention module.
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
We find two reasons why IM is not better than LOO: (1) deleting a single word from the input only marginally reduces a classifier's accuracy; and (2) a highly predictable word is always given near-zero attribution, regardless of its true importance to the classifier.
Deep Federated Learning for Autonomous Driving
We design a new Federated Autonomous Driving network (FADNet) that can improve the model stability, ensure convergence, and handle imbalanced data distribution problems while is being trained with federated learning methods.
DeepECMP: Predicting Extracellular Matrix Proteins using Deep Learning
Introduction: The extracellular matrix (ECM) is a networkof proteins and carbohydrates that has a structural and bio-chemical function.
Coarse-to-Fine Reasoning for Visual Question Answering
Bridging the semantic gap between image and question is an important step to improve the accuracy of the Visual Question Answering (VQA) task.
Ranked #1 on
Visual Question Answering (VQA)
on GQA test-dev
Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge
We design the student network such as it is light-weight and well suitable for deployment on a typical CPU.
Attention Gate in Traffic Forecasting
An attention gates filter features from the contraction path before combining with features on the expansion path, it enables our model to reduce the effect of non-traffic region features and focus more on crucial region features.
Semi-Supervised Adversarial Discriminative Domain Adaptation
Domain adaptation is a potential method to train a powerful deep neural network, which can handle the absence of labeled data.
Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery
In practice, by using a high-quality commercial RGB-D camera, our proposed visual tracking method achieves an accuracy of 1-2 degress and 2-4 mm on a model knee, which meets the standard for clinical applications.
Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images
Dense depth estimation and 3D reconstruction of a surgical scene are crucial steps in computer assisted surgery.
The DEformer: An Order-Agnostic Distribution Estimating Transformer
In this paper, we propose an alternative approach for encoding feature identities, where each feature's identity is included alongside its value in the input.
Inverting Adversarially Robust Networks for Image Synthesis
Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors.
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications.
Multiple Meta-model Quantifying for Medical Visual Question Answering
However, most of the existing medical VQA methods rely on external data for transfer learning, while the meta-data within the dataset is not fully utilized.
Ranked #5 on
Medical Visual Question Answering
on PathVQA
baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents
In many multi-agent spatiotemporal systems, agents operate under the influence of shared, unobserved variables (e. g., the play a team is executing in a game of basketball).
Ranked #1 on
Trajectory Modeling
on NBA SportVU
Graph-based Person Signature for Person Re-Identifications
In this paper, we propose a new method to effectively aggregate detailed person descriptions (attributes labels) and visual features (body parts and global features) into a graph, namely Graph-based Person Signature, and utilize Graph Convolutional Networks to learn the topological structure of the visual signature of a person.
Ranked #48 on
Person Re-Identification
on DukeMTMC-reID
An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network
This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network.
Speech Emotion Recognition using Semantic Information
In this paper, we propose a novel framework that can capture both the semantic and the paralinguistic information in the signal.
Speech Emotion Recognition
Sound
Audio and Speech Processing
WaNet -- Imperceptible Warping-based Backdoor Attack
With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years.
baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling
Multi-agent spatiotemporal modeling is a challenging task from both an algorithmic design and computational complexity perspective.
Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?
Encouraging classifiers to capture word order information improves the performance on most GLUE tasks, SQuAD 2. 0 and out-of-samples.
Natural Language Inference
Natural Language Understanding
+2
Deep Learning Framework Applied for Predicting Anomaly of Respiratory Sounds
This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles.
A Vietnamese Dataset for Evaluating Machine Reading Comprehension
Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models.
Input-Aware Dynamic Backdoor Attack
In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems.
Autonomous Navigation in Complex Environments with Deep Multimodal Fusion Network
In this work, we propose a multimodal fusion approach to address the problem of autonomous navigation in complex environments such as collapsed cites, or natural caves.
Robotics
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?
We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates.
DeepEventMine: end-to-end neural nested event extraction from biomedical texts
Motivation Recent neural approaches on event extraction from text mainly focus on flat events in general domain, while there are less attempts to detect nested and overlapping events.
Ranked #1 on
Event Extraction
on GENIA 2013
End-to-End Real-time Catheter Segmentation with Optical Flow-Guided Warping during Endovascular Intervention
In this paper, we present FW-Net, an end-to-end and real-time deep learning framework for endovascular intervention.
The shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years.
SAM: The Sensitivity of Attribution Methods to Hyperparameters
Attribution methods can provide powerful insights into the reasons for a classifier's decision.
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities.
Explaining image classifiers by removing input features using generative models
Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e. g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples.
Removing input features via a generative model to explain their attributions to classifier's decisions
Interpretability methods often measure the contribution of an input feature to an image classifier's decisions by heuristically removing it via e. g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples.
Understanding Neural Networks via Feature Visualization: A survey
A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells.
V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation
We propose V2CNet, a new deep learning framework to automatically translate the demonstration videos to commands that can be directly used in robotic applications.
Scene Understanding for Autonomous Manipulation with Deep Learning
In this study, our long-term goal is to bridge the gap between computer vision and robotics by developing visual methods that can be used in real robots.
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet.
Improving Adversarial Robustness by Encouraging Discriminative Features
Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers.
Selectivity metrics can overestimate the selectivity of units: a case study on AlexNet
These findings highlight the problem with current selectivity measures and show that new measures are required in order to provide a better assessment of learned representations in NNs.
VectorDefense: Vectorization as a Defense to Adversarial Examples
Training deep neural networks on images represented as grids of pixels has brought to light an interesting phenomenon known as adversarial examples.
Object Captioning and Retrieval with Natural Language
The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Spatial PixelCNN: Generating Images from Patches
In this paper we propose Spatial PixelCNN, a conditional autoregressive model that generates images from small patches.
Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks
We present a new method to translate videos to commands for robotic manipulation using Deep Recurrent Neural Networks (RNN).
AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images.
Real-Time 6DOF Pose Relocalization for Event Cameras with Stacked Spatial LSTM Networks
Our method first creates the event image from a list of events that occurs in a very short time interval, then a Stacked Spatial LSTM Network (SP-LSTM) is used to learn the camera pose.
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems.
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
PPGNs are composed of 1) a generator network G that is capable of drawing a wide range of image types and 2) a replaceable "condition" network C that tells the generator what to draw.
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs.
Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron.
Understanding Neural Networks Through Deep Visualization
The first is a tool that visualizes the activations produced on each layer of a trained convnet as it processes an image or video (e. g. a live webcam stream).
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99. 99% confidence (e. g. labeling with certainty that white noise static is a lion).
