Search Results for author:
Found 27 papers, 11 papers with code
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel \textit{state-object} compositions by leveraging the shared knowledge of their primitive components.
Concept Matching with Agent for Out-of-Distribution Detection
The remarkable achievements of Large Language Models (LLMs) have captivated the attention of both academia and industry, transcending their initial role in dialogue generation.
Deep Hierarchical Graph Alignment Kernels
Typical R-convolution graph kernels invoke the kernel functions that decompose graphs into non-isomorphic substructures and compare them.
Dual Expert Distillation Network for Generalized Zero-Shot Learning
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation.
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
In this work, we propose a novel method -- Convex-Concave Loss, which enables a high variance of training loss distribution by gradient descent.
Transductive Reward Inference on Graph
In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning.
Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale
Source-Free Unsupervised Domain Adaptation (SFUDA) is a challenging task where a model needs to be adapted to a new domain without access to target domain labels or source domain data.
A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization
In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization.
Nonparametric Teaching for Multiple Learners
In MINT, the teacher aims to instruct multiple learners, with each learner focusing on learning a scalar-valued target model.
Aggregation Weighting of Federated Learning via Generalization Bound Estimation
In this paper, we replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.
DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction
In this paper, we propose a novel SSL method called DualMatch, in which the class prediction jointly invokes feature embedding in a dual-level interaction manner.
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.
Nonparametric Iterative Machine Teaching
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model.
Policy Dispersion in Non-Markovian Environment
To resolve this problem, this paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment, in which a policy dispersion scheme is designed for seeking diverse policy representation.
One-shot Machine Teaching: Cost Very Few Examples to Converge Faster
Then, relying on the surjective mapping from the teaching set to the parameter, we develop a design strategy of the optimal teaching set under appropriate settings, of which two popular efficiency metrics, teaching dimension and iterative teaching dimension are one.
A Survey of Learning on Small Data: Generalization, Optimization, and Challenge
In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans.
Data-Efficient Learning via Minimizing Hyperspherical Energy
Finally, we demonstrate the empirical performance of MHEAL in a wide range of applications on data-efficient learning, including deep clustering, distribution matching, version space sampling and deep active learning.
Black-box Generalization of Machine Teaching
An inherent assumption is that this learning manner can derive those updates into the optimal hypothesis.
Hyperbolic Uncertainty Aware Semantic Segmentation
Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes.
Distribution Matching for Machine Teaching
This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters.
Bayesian Active Learning by Disagreements: A Geometric Perspective
We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation.
On the Geometry of Deep Bayesian Active Learning
To guarantee the improvements, our generalization analysis proves that, compared to typical Bayesian spherical interpretation, geodesic search with ellipsoid can derive a tighter lower error bound and achieve higher probability to obtain a nearly zero error.
Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation
In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image.
Target-Independent Active Learning via Distribution-Splitting
By discovering the connections between hypothesis and input distribution, we map the volume of version space into the number density and propose a target-independent distribution-splitting strategy with the following advantages: 1) provide theoretical guarantees on reducing label complexity and error rate as volume-splitting; 2) break the curse of initial hypothesis; 3) provide model guidance for a target-independent AL algorithm in real AL tasks.
A Structured Perspective of Volumes on Active Learning
In this paper, we approximate the version space to a structured {hypersphere} that covers most of the hypotheses, and then divide the available AL sampling approaches into two kinds of strategies: Outer Volume Sampling and Inner Volume Sampling.
Crowd Counting With Deep Negative Correlation Learning
Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks.
Ranked #9 on
Crowd Counting
on WorldExpo’10
A Divide-and-Conquer Approach to Geometric Sampling for Active Learning
With the advantages of cluster boundary points in the above two properties, we propose a Geometric Active Learning (GAL) algorithm by knight's tour.
