Search Results for author:
Found 102 papers, 41 papers with code
Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
In this paper, we relax the intra-class constraint of ArcFace to improve the robustness to label noise.
LTF: A Label Transformation Framework for Correcting Label Shift
Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems.
Label-Noise Robust Domain Adaptation
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.
Identifiable Latent Polynomial Causal Models Through the Lens of Change
However, this progress rests on the assumption that the causal relationships among latent causal variables adhere strictly to linear Gaussian models.
Causal-learn: Causal Discovery in Python
Causal discovery aims at revealing causal relations from observational data, which is a fundamental task in science and engineering.
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC).
An Efficient Transformer for Simultaneous Learning of BEV and Lane Representations in 3D Lane Detection
Our method obtains 2D and 3D lane predictions by applying the lane features to the image-view and BEV features, respectively.
CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfer
In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler).
Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
Our approach includes a density Mip-VoG for scene geometry and a feature Mip-VoG with a small MLP for view-dependent color.
Knowledge Distillation for Feature Extraction in Underwater VSLAM
This paper proposes a cross-modal knowledge distillation framework for training an underwater feature detection and matching network (UFEN).
Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community.
Generating Dynamic Kernels via Transformers for Lane Detection
While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line's global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies.
Unpaired Image-to-Image Translation With Shortest Path Regularization
In this paper, we start from a different perspective and consider the paths connecting the two domains.
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples
As selected data have high discrepancies in probabilities, the divergence of two networks can be maintained by training on such data.
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective
TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy.
3D Scene Creation and Rendering via Rough Meshes: A Lighting Transfer Avenue
However, a drawback is that the synthesized views through Neural Fields Rendering (NFR) cannot reflect the simulated lighting details on R3DMs in PBR pipelines, especially when object interactions in the 3D scene creation cause local shadows.
Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis
To explore the role of the relation between edges, this paper proposes a novel Adaptive Edge-to-Edge Interaction Learning module, which aims to enhance the point-to-point relation through modelling the edge-to-edge interaction in the local region adaptively.
Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations
This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition
Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions.
On the Sparse DAG Structure Learning Based on Adaptive Lasso
Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning.
Identifying Latent Causal Content for Multi-Source Domain Adaptation
This motivates us to propose a novel method for MSDA, which learns the invariant label distribution conditional on the latent content variable, instead of learning invariant representations.
Identifying Weight-Variant Latent Causal Models
The task of causal representation learning aims to uncover latent higher-level causal representations that affect lower-level observations.
Truncated Matrix Power Iteration for Differentiable DAG Learning
Recovering underlying Directed Acyclic Graph (DAG) structures from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem.
MetaComp: Learning to Adapt for Online Depth Completion
However, facing a new environment where the test data occurs online and differs from the training data in the RGB image content and depth sparsity, the trained model might suffer severe performance drop.
Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training.
Style Interleaved Learning for Generalizable Person Re-identification
This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains.
Domain Generalization
Generalizable Person Re-identification
+1
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention.
Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation
An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models.
Understanding Robust Overfitting of Adversarial Training and Beyond
Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.
A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning
However, because environments are not labelled, the extracted information inevitably contains redundant information unrelated to the dynamics in transition segments and thus fails to maintain a crucial property of $Z$: $Z$ should be similar in the same environment and dissimilar in different ones.
Model-based Reinforcement Learning
reinforcement-learning
+1
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
Counterfactual Fairness with Partially Known Causal Graph
Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph.
Few-Shot Font Generation by Learning Fine-Grained Local Styles
Instead of explicitly disentangling global or component-wise modeling, the cross-attention mechanism can attend to the right local styles in the reference glyphs and aggregate the reference styles into a fine-grained style representation for the given content glyphs.
On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis
We show that in causal learning, the excess risk depends on the size of the source sample at a rate of O(1/m) only if the labelling distribution between the source and target domains remains unchanged.
MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning
To alleviate the influence of the annotation bias, we perform a momentum update to ensure a consistent item representation.
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
The first one lets T compete with G to achieve maximum perturbation.
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels.
Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint
Unsupervised image-to-image (I2I) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data.
FedDAG: Federated DAG Structure Learning
To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server.
Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?
We provide reasoning why when the supports of the source and target data from overlap, any map of $X$ that is fixed across domains may not be suitable for domain adaptation via invariant features.
CRIS: CLIP-Driven Referring Image Segmentation
In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
Contrastive Learning
Generalized Referring Expression Segmentation
+3
Instrumental Variable-Driven Domain Generalization with Unobserved Confounders
Meanwhile, the existing of unobserved confounders which affect the input features and labels simultaneously cause spurious correlation and hinder the learning of the invariant relationship contained in the conditional distribution.
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?
Existing methods for learning with noisy labels can be generally divided into two categories: (1) sample selection and label correction based on the memorization effect of neural networks; (2) loss correction with the transition matrix.
Co-variance: Tackling Noisy Labels with Sample Selection by Emphasizing High-variance Examples
The sample selection approach is popular in learning with noisy labels, which tends to select potentially clean data out of noisy data for robust training.
Unaligned Image-to-Image Translation by Learning to Reweight
An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e. g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain.
Instance-dependent Label-noise Learning under a Structural Causal Model
In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier.
Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification
In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501.
Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision
In this paper, we propose a weakly supervised do-main adaptation setting, in which we can partially label newdatasets with bounding boxes, which are easier and cheaperto obtain than segmentation masks.
Exploring Set Similarity for Dense Self-supervised Representation Learning
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
Kernel Mean Estimation by Marginalized Corrupted Distributions
Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms.
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
Instance Correction for Learning with Open-set Noisy Labels
Lots of approaches, e. g., loss correction and label correction, cannot handle such open-set noisy labels well, since they need training data and test data to share the same label space, which does not hold for learning with open-set noisy labels.
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try.
Ranked #26 on
Image Classification
on mini WebVision 1.0
Learning with Group Noise
Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels.
Score-based Causal Discovery from Heterogeneous Data
Most algorithms in causal discovery consider a single domain with a fixed distribution.
Not All Operations Contribute Equally: Hierarchical Operation-Adaptive Predictor for Neural Architecture Search
Despite their efficiency, current graph-based predictors treat all operations equally, resulting in biased topological knowledge of cell architectures.
Improving robustness of softmax corss-entropy loss via inference information
Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.
Minimal Geometry-Distortion Constraint for Unsupervised Image-to-Image Translation
Unsupervised image-to-image (I2I) translation, which aims to learn a domain mapping function without paired data, is very challenging because the function is highly under-constrained.
Contextual Graph Reasoning Networks
Graph Reasoning has shown great potential recently in modeling long-range dependencies, which are crucial for various computer vision tasks.
Domain Generalization via Entropy Regularization
To arrive at this, some methods introduce a domain discriminator through adversarial learning to match the feature distributions in multiple source domains.
Ranked #40 on
Domain Generalization
on PACS
Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning
Image-based 3D shape retrieval (IBSR) aims to find the corresponding 3D shape of a given 2D image from a large 3D shape database.
Deep Learning is Singular, and That's Good
In singular models, the optimal set of parameters forms an analytic set with singularities and classical statistical inference cannot be applied to such models.
Class2Simi: A New Perspective on Learning with Label Noise
It is worthwhile to perform the transformation: We prove that the noise rate for the noisy similarity labels is lower than that of the noisy class labels, because similarity labels themselves are robust to noise.
3D-FUTURE: 3D Furniture shape with TextURE
The 3D CAD shapes in current 3D benchmarks are mostly collected from online model repositories.
3D Object Reconstruction From A Single Image
3D Shape Retrieval
+4
Short-Term and Long-Term Context Aggregation Network for Video Inpainting
Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal.
Adaptive Context-Aware Multi-Modal Network for Depth Completion
Furthermore, considering the mutli-modality of input data, we exploit the graph propagation on the two modalities respectively to extract multi-modal representations.
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image.
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not.
Part-dependent Label Noise: Towards Instance-dependent Label Noise
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise.
Multi-Class Classification from Noisy-Similarity-Labeled Data
We further estimate the transition matrix from only noisy data and build a novel learning system to learn a classifier which can assign noise-free class labels for instances.
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Hitherto, the distributional-assumption-free CPE methods rely on a critical assumption that the support of the positive data distribution cannot be contained in the support of the negative data distribution.
Domain Adaptation as a Problem of Inference on Graphical Models
Such a graphical model distinguishes between constant and varied modules of the distribution and specifies the properties of the changes across domains, which serves as prior knowledge of the changing modules for the purpose of deriving the posterior of the target variable $Y$ in the target domain.
Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering
The learned SSCM gives the specific causal knowledge for each individual as well as the general trend over the population.
Twin Auxilary Classifiers GAN
One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN) that generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier.
Ranked #2 on
Image Generation
on CIFAR-100
Learning Multi-level Weight-centric Features for Few-shot Learning
Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning.
Likelihood-Free Overcomplete ICA and Applications in Causal Discovery
Causal discovery witnessed significant progress over the past decades.
Learning Depth from Monocular Videos Using Synthetic Data: A Temporally-Consistent Domain Adaptation Approach
Due to the stylish difference between synthetic and real images, we propose a temporally-consistent domain adaptation (TCDA) approach that simultaneously explores labels in the synthetic domain and temporal constraints in the videos to improve style transfer and depth prediction.
Twin Auxiliary Classifiers GAN
One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier.
Ranked #2 on
Conditional Image Generation
on CIFAR-100
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models
In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments.
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures.
Ranked #57 on
Monocular Depth Estimation
on KITTI Eigen split
Generative-Discriminative Complementary Learning
The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases.
Robust Angular Local Descriptor Learning
In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2].
Modeling Dynamic Missingness of Implicit Feedback for Recommendation
Recent studies modeled \emph{exposure}, a latent missingness variable which indicates whether an item is missing to a user, to give each missing entry a confidence of being negative feedback.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
Unsupervised domain mapping aims to learn a function to translate domain X to Y by a function GXY in the absence of paired examples.
Correcting the Triplet Selection Bias for Triplet Loss
Considering that the number of triplets grows cubically with the size of training data, triplet mining is thus indispensable for efficiently training with triplet loss.
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Under the assumption that the conditional distribution $P(Y|X)$ remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation $T(X)$ by minimizing the discrepancy of the marginal distribution $P(T(X))$.
Ranked #64 on
Domain Generalization
on PACS
Domain Generalization via Conditional Invariant Representation
With the conditional invariant representation, the invariance of the joint distribution $\mathbb{P}(h(X), Y)$ can be guaranteed if the class prior $\mathbb{P}(Y)$ does not change across training and test domains.
Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector
Our model consists of three mutually dependent modules which regulate each other: (1) a discriminative network that learns a fixed-length representation from local features and maps them to disease severity; (2) an attention mechanism that provides interpretability by focusing on the areas of the anatomy that contribute the most to the prediction task; and (3) a generative network that encourages the diversity of the local latent features.
MoE-SPNet: A Mixture-of-Experts Scene Parsing Network
In the proposed networks, different levels of features at each spatial location are adaptively re-weighted according to the local structure and surrounding contextual information before aggregation.
Deep Ordinal Regression Network for Monocular Depth Estimation
These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions.
Ranked #12 on
Depth Estimation
on NYU-Depth V2
An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution.
Causal Generative Domain Adaptation Networks
For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains.
Learning with Biased Complementary Labels
We therefore reason that the transition probabilities will be different.
A Coarse-Fine Network for Keypoint Localization
To target this problem, we develop a keypoint localization network composed of several coarse detector branches, each of which is built on top of a feature layer in a CNN, and a fine detector branch built on top of multiple feature layers.
A Compromise Principle in Deep Monocular Depth Estimation
However, we find that training a network to predict a high spatial resolution continuous depth map often suffers from poor local solutions.
Transfer Learning with Label Noise
However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels.
Causal Discovery in the Presence of Measurement Error: Identifiability Conditions
This problem has received much attention in multiple fields, but it is not clear to what extent the causal model for the measurement-error-free variables can be identified in the presence of measurement error with unknown variance.
Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components
A widely applied approach to causal inference from a non-experimental time series $X$, often referred to as "(linear) Granger causal analysis", is to regress present on past and interpret the regression matrix $\hat{B}$ causally.
