Search Results for author:
Found 49 papers, 16 papers with code
An Intermediate Fusion ViT Enables Efficient Text-Image Alignment in Diffusion Models
Diffusion models have been widely used for conditional data cross-modal generation tasks such as text-to-image and text-to-video.
Cross-domain Multi-modal Few-shot Object Detection via Rich Text
Cross-modal feature extraction and integration have led to steady performance improvements in few-shot learning tasks due to generating richer features.
CRISPR: Ensemble Model
This is because most existing methods are trained on separate datasets with different genes and cells, which limits their generalizability.
Meta-Tasks: An alternative view on Meta-Learning Regularization
The ability to generalize effectively on both novel and training tasks is a significant barrier to FSL.
Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay
Our solution is based on stabilizing the learned internal distribution to enhances the model generalization on new domains.
Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks
We propose a transformer-based CL framework focusing on learning tasks that involve both vision and language, known as Vision-and-Language (VaL) tasks.
Unsupervised Domain Adaptation Using Compact Internal Representations
To further enhance the performance of unsupervised domain adaptation (UDA), we develop an additional technique which makes the internal distribution of the source domain more compact, thereby improving the model's ability to generalize in the target domain. We demonstrate that by increasing the margins between data representations for different classes in the embedding space, we can improve the model performance for UDA.
Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptation
By applying self-supervised learning, the algorithm learns to align the representations of event-based data with those from frame-based camera data, thereby facilitating knowledge transfer. Furthermore, the inclusion of uncorrelated conditioning ensures that the adapted model effectively distinguishes between event-based and conventional data, enhancing its ability to classify event-based images accurately. Through empirical experimentation and evaluation, we demonstrate that our algorithm surpasses existing approaches designed for the same purpose using two benchmarks.
Unsupervised Federated Domain Adaptation for Segmentation of MRI Images
Our approach enables the transfer of knowledge from several annotated source domains to adapt a model for effective use in an unannotated target domain.
Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations
Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance.
Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net
Recently, diffusion models have been used successfully to fit distributions for cross-modal data translation and multimodal data generation.
Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning
We use augmented samples as the query set during the training phase of the unsupervised meta-learning.
Class-Incremental Learning Using Generative Experience Replay Based on Time-aware Regularization
Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning.
Robust Internal Representations for Domain Generalization
This paper which is part of the New Faculty Highlights Invited Speaker Program of AAAI'23, serves as a comprehensive survey of my research in transfer learning by utilizing embedding spaces.
Improved Region Proposal Network for Enhanced Few-Shot Object Detection
Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes.
History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion
Temporal knowledge graph (TKG) completion models typically rely on having access to the entire graph during training.
Cognitively Inspired Cross-Modal Data Generation Using Diffusion Models
Most existing cross-modal generative methods based on diffusion models use guidance to provide control over the latent space to enable conditional generation across different modalities.
Low-Shot Learning for Fictional Claim Verification
In this paper, we study the problem of claim verification in the context of claims about fictional stories in a low-shot learning setting.
I2I: Initializing Adapters with Improvised Knowledge
We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters.
Explainable Artificial Intelligence Architecture for Melanoma Diagnosis Using Indicator Localization and Self-Supervised Learning
Melanoma is a prevalent lethal type of cancer that is treatable if diagnosed at early stages of development.
Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation
The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications.
Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representation
We propose a novel binarized regularization to facilitate learning of binary concepts to improve the quality of data generation in autoencoders.
Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning
Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers.
Identification of Novel Classes for Improving Few-Shot Object Detection
Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects.
Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data
To navigate these obstacles, we develop the Denoising and Nuclear-Norm Wasserstein Adaptation Network (DNAN).
Preserving Fairness in AI under Domain Shift
Our algorithm is based on updating the model such that the internal representation of data remains unbiased despite distributional shifts in the input space.
Unsupervised Model Adaptation for Source-free Segmentation of Medical Images
We rely on an approximation of the source latent features at adaptation time, and create a joint source/target embedding space by minimizing a distributional distance metric based on optimal transport.
Increasing Model Generalizability for Unsupervised Domain Adaptation
A dominant approach for addressing unsupervised domain adaptation is to map data points for the source and the target domains into an embedding space which is modeled as the output-space of a shared deep encoder.
Automating Detection of Papilledema in Pediatric Fundus Images with Explainable Machine Learning
Papilledema is an ophthalmic neurologic disorder in which increased intracranial pressure leads to swelling of the optic nerves.
CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
Existing CL benchmarks have facilitated research on task adaptation and mitigating "catastrophic forgetting", but are limited to vision-only and language-only tasks.
Lifelong Domain Adaptation via Consolidated Internal Distribution
We develop an algorithm to address unsupervised domain adaptation (UDA) in continual learning (CL) settings.
Cognitively Inspired Learning of Incremental Drifting Concepts
Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences.
Detection and Continual Learning of Novel Face Presentation Attacks
Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research.
Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
We introduce a new domain adaptation method which induces large margins between different classes in an embedding space.
Secure Domain Adaptation with Multiple Sources
Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence.
Domain Adaptation for the Segmentation of Confidential Medical Images
In this work, we develop an algorithm for UDA where the source domain data is inaccessible during target adaptation.
Learning a Max-Margin Classifier for Cross-Domain Sentiment Analysis
Large margins in the source domain help to reduce the effect of ``domain shift'' on the performance of a trained classifier in the target domain.
One-shot Learning for Temporal Knowledge Graphs
Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times.
Unsupervised Model Adaptation for Continual Semantic Segmentation
We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain.
Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions
We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible.
Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized.
Generative Continual Concept Learning
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge.
Zero-Shot Image Classification Using Coupled Dictionary Embedding
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes.
Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay
We sample from this distribution and utilize experience replay to avoid forgetting and simultaneously accumulate new knowledge to the abstract distribution in order to couple the current task with past experience.
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer.
Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience.
Joint Dictionaries for Zero-Shot Learning
A classic approach toward zero-shot learning (ZSL) is to map the input domain to a set of semantically meaningful attributes that could be used later on to classify unseen classes of data (e. g. visual data).
Image Super-Resolution Based on Sparsity Prior via Smoothed $l_0$ Norm
However, sparse representation of a signal over a known dictionary is an ill-posed, combinatorial optimization problem.
