Search Results for author:
Found 65 papers, 23 papers with code
Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge
Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling.
On the Benefits of Attribute-Driven Graph Domain Adaptation
Graph Domain Adaptation (GDA) addresses a pressing challenge in cross-network learning, particularly pertinent due to the absence of labeled data in real-world graph datasets.
ZETA: Leveraging Z-order Curves for Efficient Top-k Attention
However, causal masks require the current query token to only attend to past tokens, preventing the existing top-$k$ attention method from efficiently searching for the most relevant tokens in parallel, thereby limiting training efficiency.
Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.
Textualize Visual Prompt for Image Editing via Diffusion Bridge
Visual prompt, a pair of before-and-after edited images, can convey indescribable imagery transformations and prosper in image editing.
Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression
Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning.
LVP-CLIP:Revisiting CLIP for Continual Learning with Label Vector Pool
Traditional CLIP-based classification methods identify the most similar text label for a test image by comparing their embeddings.
Learning from Noisy Labels via Conditional Distributionally Robust Optimization
Moreover, to devise an efficient algorithm for CDRO, we derive a closed-form expression for the empirical robust risk and the optimal Lagrange multiplier of the dual problem, facilitating a principled balance between robustness and model fitting.
Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents.
MABR: A Multilayer Adversarial Bias Removal Approach Without Prior Bias Knowledge
Models trained on real-world data often mirror and exacerbate existing social biases.
Intersectional Unfairness Discovery
To further evaluate the generated unseen but possible unfair intersectional sensitive attributes, we formulate them as prompts and use modern generative AI to produce new texts and images.
Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations
Specifically, we first show that under certain conditions, the residual loss of PINNs can be globally minimized by a wide neural network.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter
Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline.
Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces
Domain adaptation has gained significant attention to address the nonstationarity problem in electroencephalography (EEG) data in motor imagery (MI) classification.
Generalizing across Temporal Domains with Koopman Operators
By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains.
Decentralized Federated Learning: A Survey on Security and Privacy
Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages.
Masked Attribute Description Embedding for Cloth-Changing Person Re-identification
To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model.
Iterative Feedback Network for Unsupervised Point Cloud Registration
In this paper, we propose a novel Iterative Feedback Network (IFNet) for unsupervised point cloud registration, in which the representation of low-level features is efficiently enriched by rerouting subsequent high-level features.
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner.
Toward Open-ended Embodied Tasks Solving
Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years.
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method.
Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimization
Meanwhile, the upstream model (server) is updated with first-order optimization (FOO) locally, which significantly improves the convergence rate, making it feasible to train the large models without compromising privacy and security.
VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild
In this work, we examine two in-the-wild HAR datasets and DivideMix, a state-of-the-art learning with noise labels (LNL) method to understand the extent and impacts of noisy labels in training data.
Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training
We propose a novel visual similarity learning paradigm, Geometric Visual Similarity Learning, which embeds the prior of topological invariance into the measurement of the inter-image similarity for consistent representation of semantic regions.
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation
We demonstrate that domain labels are not directly necessary for BTDA if categorical distributions of various domains are sufficiently aligned even facing the imbalance of domains and the label distribution shift of classes.
Ranked #1 on
Multi-target Domain Adaptation
on Office-Home
Blended-target Domain Adaptation
Label shift of blended-target domain adaptation
+1
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
We also prove that such a difference makes existing LLN methods that rely on their distribution assumptions unable to address the label noise in SFDA.
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment.
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.
On Learning Fairness and Accuracy on Multiple Subgroups
In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors.
Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks
Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs).
Evolving Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Fair Representation Learning through Implicit Path Alignment
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups.
Weakly Supervised Object Localization as Domain Adaption
To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
On Learning Contrastive Representations for Learning with Noisy Labels
To address this issue, we focus on learning robust contrastive representations of data on which the classifier is hard to memorize the label noise under the CE loss.
CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator
With the prevalence of wearable devices, inertial measurement unit (IMU) data has been utilized in monitoring and assessment of human mobility such as human activity recognition (HAR).
Domain-Augmented Domain Adaptation
Unsupervised domain adaptation (UDA) enables knowledge transfer from the labelled source domain to the unlabeled target domain by reducing the cross-domain discrepancy.
Gap Minimization for Knowledge Sharing and Transfer
Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.
Full-attention based Neural Architecture Search using Context Auto-regression
Thus, it is appropriate to consider using NAS methods to discover a better self-attention architecture automatically.
Directional Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
On the benefits of representation regularization in invariance based domain generalization
Our regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms for invariant representation learning.
Aggregating From Multiple Target-Shifted Sources
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain.
Multi-task Learning by Leveraging the Semantic Information
To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions.
Unified Principles For Multi-Source Transfer Learning Under Label Shifts
We study the label shift problem in multi-source transfer learning and derive new generic principles to control the target generalization risk.
Invariant Feature Learning for Sensor-based Human Activity Recognition
In recent years, many deep models have been applied to HAR problems.
Uncertainty Estimation and Sample Selection for Crowd Counting
We present sample selection strategies which make use of the density and uncertainty of predictions from the networks trained on one domain to select the informative images from a target domain of interest to acquire human annotation.
Distribution Matching for Crowd Counting
Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point.
Ranked #4 on
Crowd Counting
on UCF CC 50
Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images
Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images.
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence.
Domain Generalization via Optimal Transport with Metric Similarity Learning
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems.
Active Vision for Early Recognition of Human Actions
We propose a method for early recognition of human actions, one that can take advantages of multiple cameras while satisfying the constraints due to limited communication bandwidth and processing power.
Discriminative Active Learning for Domain Adaptation
To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation.
MEUZZ: Smart Seed Scheduling for Hybrid Fuzzing
Seed scheduling is a prominent factor in determining the yields of hybrid fuzzing.
Multi-view Subspace Clustering via Partition Fusion
Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way.
Transfer Learning via Minimizing the Performance Gap Between Domains
We propose a new principle for transfer learning, based on a straightforward intuition: if two domains are similar to each other, the model trained on one domain should also perform well on the other domain, and vice versa.
Deep Active Learning: Unified and Principled Method for Query and Training
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning.
Efficient Projection-Free Online Methods with Stochastic Recursive Gradient
This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems.
Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images
This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images.
Clustering with Similarity Preserving
A key step of graph-based approach is the similarity graph construction.
A Principled Approach for Learning Task Similarity in Multitask Learning
Hence, an important aspect of multitask learning is to understand the similarities within a set of tasks.
Sequence-to-Segment Networks for Segment Detection
Detecting segments of interest from an input sequence is a challenging problem which often requires not only good knowledge of individual target segments, but also contextual understanding of the entire input sequence and the relationships between the target segments.
Leveraging Disease Progression Learning for Medical Image Recognition
Unlike natural images, medical images often have intrinsic characteristics that can be leveraged for neural network learning.
X-ray Scattering Image Classification Using Deep Learning
In this paper, we explore the use of deep learning to develop methods for automatically analyzing x-ray scattering images.
Online Ensemble Learning for Imbalanced Data Streams
While both cost-sensitive learning and online learning have been studied extensively, the effort in simultaneously dealing with these two issues is limited.
