Search Results for author:
Found 52 papers, 26 papers with code
Exploring Task-Level Optimal Prompts for Visual In-Context Learning
With the development of Vision Foundation Models (VFMs) in recent years, Visual In-Context Learning (VICL) has become a better choice compared to modifying models in most scenarios.
Out-Of-Distribution Detection with Diversification (Provably)
Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models.
Test-Time Dynamic Image Fusion
The decomposed components represent the effective information from the source data, thus the gap between them reflects the Relative Dominability (RD) of the uni-source data in constructing the fusion image.
COME: Test-time adaption by Conservatively Minimizing Entropy
Machine learning models must continuously self-adjust themselves for novel data distribution in the open world.
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
To our best knowledge, this work is the first principled OOD detection method that achieves state-of-the-art OOD detection performance without compromising OOD generalization ability.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
DOTA: Distributional Test-Time Adaptation of Vision-Language Models
Instead of naively memorizing representative test samples, Dota continually estimates the distributions of test samples, allowing the model to continually adapt to the deployment environment.
Common and Rare Fundus Diseases Identification Using Vision-Language Foundation Model with Knowledge of Over 400 Diseases
Here we introduce RetiZero, a vision-language foundation model that leverages knowledge from over 400 fundus diseases.
Predictive Dynamic Fusion
Accordingly, we further propose a relative calibration strategy to calibrate the predicted Co-Belief for potential uncertainty.
Confidence-aware multi-modality learning for eye disease screening
In this study, we propose a novel multi-modality evidential fusion pipeline for eye disease screening.
Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of scenarios, including autonomous driving and medical diagnosis.
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.
Selective Learning: Towards Robust Calibration with Dynamic Regularization
The objective can be understood as seeking a model that fits the ground-truth labels by increasing the confidence while also maximizing the entropy of predicted probabilities by decreasing the confidence.
Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models
Recent advancements in large vision-language models (LVLMs) have demonstrated impressive capability in visual information understanding with human language.
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection.
Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Specifically, we discuss the differences between discriminative and generative models using content moderation as an example.
Semantic Equivariant Mixup
Then a generic mixup regularization at the representation level is proposed, which can further regularize the model with the semantic information in mixed samples.
Proceedings of the 40th International Conference on Machine Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
Provable Dynamic Fusion for Low-Quality Multimodal Data
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction.
dugMatting: Decomposed-Uncertainty-Guided Matting
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing.
Calibrating Multimodal Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
Semantic Invariant Multi-view Clustering with Fully Incomplete Information
To address this problem, we present a novel framework called SeMantic Invariance LEarning (SMILE) for multi-view clustering with incomplete information that does not require any paired samples.
Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification
Second, the quality of the imputed data itself is of high uncertainty.
Reweighted Mixup for Subpopulation Shift
Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions.
Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification
Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies.
Balanced Audiovisual Dataset for Imbalance Analysis
We surprisingly find that: the multimodal models with existing imbalance algorithms consistently perform worse than the unimodal one on specific subsets, in accordance with the modality bias.
Graph Matching with Bi-level Noisy Correspondence
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC).
Ranked #1 on
Graph Matching
on Willow Object Class
UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup
Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset.
Trusted Multi-View Classification with Dynamic Evidential Fusion
With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level.
Uncertainty-Aware Multi-View Representation Learning
Under the help of uncertainty, DUA-Nets weigh each view of individual sample according to data quality so that the high-quality samples (or views) can be fully exploited while the effects from the noisy samples (or views) will be alleviated.
Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification
To the best of our knowledge, this is the first work to jointly model both feature and modality variation for different samples to provide trustworthy fusion in multi-modal classification.
Trustworthy Long-Tailed Classification
To address these issues, we propose a Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework.
Ranked #21 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
Multimodal regression is a fundamental task, which integrates the information from different sources to improve the performance of follow-up applications.
Identifying Incorrect Classifications with Balanced Uncertainty
Uncertainty estimation is critical for cost-sensitive deep-learning applications (i. e. disease diagnosis).
Trusted Multi-View Classification
To this end, we propose a novel multi-view classification method, termed trusted multi-view classification, which provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level.
Multi-View Disentangled Representation
Learning effective representations for data with multiple views is crucial in machine learning and pattern recognition.
Deep Partial Multi-View Learning
Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing.
LRA: an accelerated rough set framework based on local redundancy of attribute for feature selection
Based on the theorem, we propose the LRA framework for accelerating rough set algorithms.
SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels.
M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
Diagnosis of Coronavirus Disease 2019 (COVID-19) with Structured Latent Multi-View Representation Learning
In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images.
Ball k-means
The assigned cluster of the points in the stable area is not changed in the current iteration while the points in the annulus area will be adjusted within a few neighbor clusters in the current iteration.
CPM-Nets: Cross Partial Multi-View Networks
Despite multi-view learning progressed fast in past decades, it is still challenging due to the difficulty in modeling complex correlation among different views, especially under the context of view missing.
AE2-Nets: Autoencoder in Autoencoder Networks
The proposed method has the following merits: (1) our model jointly performs view-specific representation learning (with the inner autoencoder networks) and multi-view information encoding (with the outer autoencoder networks) in a unified framework; (2) due to the degradation process from the latent representation to each single view, our model flexibly balances the complementarity and consistence among multiple views.
Unsupervised Degradation Learning for Single Image Super-Resolution
Specifically, we propose a degradation network to model the real-world degradation process from HR to LR via generative adversarial networks, and these generated realistic LR images paired with real-world HR images are exploited for training the SR reconstruction network, forming the first cycle.
Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region.
Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion
Stereoscopic perception is an important part of human visual system that allows the brain to perceive depth.
K-means clustering for efficient and robust registration of multi-view point sets
Subsequently, the shape comprised by all cluster centroids is used to sequentially estimate the rigid transformation for each point set.
Latent Multi-View Subspace Clustering
In this paper, we propose a novel Latent Multi-view Subspace Clustering (LMSC) method, which clusters data points with latent representation and simultaneously explores underlying complementary information from multiple views.
Exclusivity-Consistency Regularized Multi-View Subspace Clustering
Multi-view subspace clustering aims to partition a set of multi-source data into their underlying groups.
SketchNet: Sketch Classification With Web Images
In this study, we present a weakly supervised approach that discovers the discriminative structures of sketch images, given pairs of sketch images and web images.
Low-Rank Tensor Constrained Multiview Subspace Clustering
We introduce a low-rank tensor constraint to explore the complementary information from multiple views and, accordingly, establish a novel method called Low-rank Tensor constrained Multiview Subspace Clustering (LT-MSC).
Diversity-Induced Multi-View Subspace Clustering
In this paper, we focus on how to boost the multi-view clustering by exploring the complementary information among multi-view features.
