Search Results for author:
Found 58 papers, 12 papers with code
PIE: Physics-inspired Low-light Enhancement
In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE.
All Beings Are Equal in Open Set Recognition
In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given $K$ known classes as an additional $K$+$1$-th class to explicitly model potential open space.
TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning
Learning universal time series representations applicable to various types of downstream tasks is challenging but valuable in real applications.
Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
No Regularization is Needed: An Efficient and Effective Model for Incomplete Label Distribution Learning
Then, by using the prior of degrees, we design a weighted scheme and verify its effectiveness.
Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning
Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise.
ALL-E: Aesthetics-guided Low-light Image Enhancement
In this paper, we propose a new paradigm, i. e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward.
Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems
Moreover, we provide a solid convergence analysis for our DM-GDA method, and prove that it obtains a near-optimal gradient complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of the nonconvex-PL stochastic minimax problems, which reaches the lower bound of nonconvex stochastic optimization.
Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels
In Multi-Label Learning (MLL), it is extremely challenging to accurately annotate every appearing object due to expensive costs and limited knowledge.
PointSmile: Point Self-supervised Learning via Curriculum Mutual Information
From the perspective of how-and-what-to-learn, PointSmile is designed to imitate human curriculum learning, i. e., starting with an easy curriculum and gradually increasing the difficulty of that curriculum.
Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
Adaptive Federated Minimax Optimization with Lower Complexities
To fill this gap, in the paper, we study a class of nonconvex minimax optimization, and propose an efficient adaptive federated minimax optimization algorithm (i. e., AdaFGDA) to solve these distributed minimax problems.
Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels
However, these CL methods fail to be directly adapted to multi-label image classification due to the difficulty in defining the positive and negative instances to contrast a given anchor image in multi-label scenario, let the label missing one alone, implying that borrowing a commonly-used way from contrastive multi-class learning to define them will incur a lot of false negative instances unfavorable for learning.
Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition
For these issues, we propose the Class-aware Universum Inspired Re-balance Learning(CaUIRL) for long-tailed recognition, which endows the Universum with class-aware ability to re-balance individual minority classes from both sample quantity and quality.
Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox
In this paper, we propose a new UniDA method with adaptive Unknown Authentication by Classifier Paradox (UACP), considering that samples with paradoxical predictions are probably unknowns belonging to none of the source classes.
Dual-Correction Adaptation Network for Noisy Knowledge Transfer
Previous unsupervised domain adaptation (UDA) methods aim to promote target learning via a single-directional knowledge transfer from label-rich source domain to unlabeled target domain, while its reverse adaption from target to source has not jointly been considered yet so far.
Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks
Detecting abnormal nodes from attributed networks is of great importance in many real applications, such as financial fraud detection and cyber security.
View-labels Are Indispensable: A Multifacet Complementarity Study of Multi-view Clustering
Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC).
A Novel Splitting Criterion Inspired by Geometric Mean Metric Learning for Decision Tree
Decision tree (DT) attracts persistent research attention due to its impressive empirical performance and interpretability in numerous applications.
Universum-inspired Supervised Contrastive Learning
In this paper, inspired by Universum Learning which uses out-of-class samples to assist the target tasks, we investigate Mixup from a largely under-explored perspective - the potential to generate in-domain samples that belong to none of the target classes, that is, universum.
Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s), then 2) transferring the representations to assist downstream task(s).
Jacobian Norm for Unsupervised Source-Free Domain Adaptation
Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain.
A Similarity-based Framework for Classification Task
Similarity-based method gives rise to a new class of methods for multi-label learning and also achieves promising performance.
Can Adversarial Training Be Manipulated By Non-Robust Features?
Under this threat, we show that adversarial training using a conventional defense budget $\epsilon$ provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by $\epsilon$-bounded perturbation.
Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task
Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks.
Partial Domain Adaptation without Domain Alignment
Considering the difficulty of perfect alignment in solving PDA, we turn to focus on the model smoothness while discard the riskier domain alignment to enhance the adaptability of the model.
Rectified Euler k-means and Beyond
To eliminate the deviation, we propose two Rectified Euler k-means methods, i. e., REK1 and REK2, which retain the merits of EulerK while acquire real centroids residing on the mapped space to better characterize the data structures.
Is It Time to Redefine the Classification Task for Deep Learning Systems?
Many works have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial examples.
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries
Recently, much research has been devoted to improving the model robustness by training with noise perturbations.
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by slightly perturbing the features of correctly labeled training examples.
Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs
However, to the best of our knowledge, there is limited study on twofold heterogeneous MTL (THMTL) scenario where the input and the output spaces are both inconsistent or heterogeneous.
With False Friends Like These, Who Can Notice Mistakes?
In this paper, we unveil the threat of hypocritical examples -- inputs that are originally misclassified yet perturbed by a false friend to force correct predictions.
Leave Zero Out: Towards a No-Cross-Validation Approach for Model Selection
On the one hand, for small data cases, CV suffers a conservatively biased estimation, since some part of the limited data has to hold out for validation.
With False Friends Like These, Who Can Have Self-Knowledge?
In this paper, we formalize the hypocritical risk for the first time and propose a defense method specialized for hypocritical examples by minimizing the tradeoff between natural risk and an upper bound of hypocritical risk.
Convex Subspace Clustering by Adaptive Block Diagonal Representation
While the latter directly or explicitly imposes the block diagonal structure prior such as block diagonal representation (BDR) to ensure so-desired block diagonalty even if the data is noisy but at the expense of losing the convexity that the former's objective possesses.
Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces
Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift.
Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
Our theoretical analysis shows that the online SPIDER-ADMM has the IFO complexity of $\mathcal{O}(\epsilon^{-\frac{3}{2}})$, which improves the existing best results by a factor of $\mathcal{O}(\epsilon^{-\frac{1}{2}})$.
Accelerated Stochastic Gradient-free and Projection-free Methods
To relax the large batches required in the Acc-SZOFW, we further propose a novel accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW*) based on a new variance reduced technique of STORM, which still reaches the function query complexity of $O(d\epsilon^{-3})$ in the stochastic problem without relying on any large batches.
A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning
In aligning, we characterize the global and local structures of multiple labels to be high-rank and low-rank, respectively.
A Centroid Auto-Fused Hierarchical Fuzzy c-Means Clustering
Like k-means and Gaussian Mixture Model (GMM), fuzzy c-means (FCM) with soft partition has also become a popular clustering algorithm and still is extensively studied.
Expand Globally, Shrink Locally: Discriminant Multi-label Learning with Missing Labels
In multi-label learning, the issue of missing labels brings a major challenge.
A Multi-view Perspective of Self-supervised Learning
Specifically, a simple multi-view learning framework is specially designed (SSL-MV), which assists the feature learning of downstream tasks (original view) through the same tasks on the augmented views.
Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
On the other hand, for G-OSR, introducing such semantic information of known classes not only improves the recognition performance but also endows OSR with the cognitive ability of unknown classes.
Zeroth-Order Stochastic Alternating Direction Method of Multipliers for Nonconvex Nonsmooth Optimization
In particular, our methods not only reach the best convergence rate $O(1/T)$ for the nonconvex optimization, but also are able to effectively solve many complex machine learning problems with multiple regularized penalties and constraints.
Doubly Aligned Incomplete Multi-view Clustering
Specifically, on the one hand, DAIMC utilizes the given instance alignment information to learn a common latent feature matrix for all the views.
One-Pass Incomplete Multi-view Clustering
Real data are often with multiple modalities or from multiple heterogeneous sources, thus forming so-called multi-view data, which receives more and more attentions in machine learning.
Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems.
Recent Advances in Open Set Recognition: A Survey
A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with the unseen ones.
Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
Unsupervised domain adaptation (UDA) aims to learn the unlabeled target domain by transferring the knowledge of the labeled source domain.
Collective decision for open set recognition
In open set recognition (OSR), almost all existing methods are designed specially for recognizing individual instances, even these instances are collectively coming in batch.
Active Feature Acquisition with Supervised Matrix Completion
Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance.
Mini-Batch Stochastic ADMMs for Nonconvex Nonsmooth Optimization
Moreover, we extend the mini-batch stochastic gradient method to both the nonconvex SVRG-ADMM and SAGA-ADMM proposed in our initial manuscript \cite{huang2016stochastic}, and prove these mini-batch stochastic ADMMs also reaches the convergence rate of $O(1/T)$ without condition on the mini-batch size.
Linear Convergence of Accelerated Stochastic Gradient Descent for Nonconvex Nonsmooth Optimization
To the best of our knowledge, it is first proved that the accelerated SGD method converges linearly to the local minimum of the nonconvex optimization.
Stochastic Alternating Direction Method of Multipliers with Variance Reduction for Nonconvex Optimization
Specifically, the first class called the nonconvex stochastic variance reduced gradient ADMM (SVRG-ADMM), uses a multi-stage scheme to progressively reduce the variance of stochastic gradients.
Joint Gender Classification and Age Estimation by Nearly Orthogonalizing Their Semantic Spaces
In human face-based biometrics, gender classification and age estimation are two typical learning tasks.
A Unified Gender-Aware Age Estimation
Although leading to promotion of age estimation performance, such a concatenation not only likely confuses the semantics between the gender and age, but also ignores the aging discrepancy between the male and the female.
Joint Representation Classification for Collective Face Recognition
In this paper, a joint representation classification (JRC) for collective face recognition is proposed.
Tri-Subject Kinship Verification: Understanding the Core of A Family
One major challenge in computer vision is to go beyond the modeling of individual objects and to investigate the bi- (one-versus-one) or tri- (one-versus-two) relationship among multiple visual entities, answering such questions as whether a child in a photo belongs to given parents.
