Search Results for author:
Found 55 papers, 30 papers with code
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.
A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators
The selective classifier (SC) has garnered increasing interest in areas such as medical diagnostics, autonomous driving, and the justice system.
Redundancy-Aware Camera Selection for Indoor Scene Neural Rendering
Based on this matrix, we use the Intra-List Diversity (ILD) metric to assess camera redundancy, formulating the camera selection task as an optimization problem.
AC-IND: Sparse CT reconstruction based on attenuation coefficient estimation and implicit neural distribution
In this work, we incorporate a powerful prior: the total number of material categories of objects.
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
For example, we demonstrate that pruning up to 75% of experts in Mixtral $8\times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss.
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information.
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
We reveal some findings: (1) Teaching materials that make it easier for students to learn have clearer and more accurate logic when using in-context learning as the student's "learning" method; (2) Weak-to-strong generalization: LbT might help improve strong models by teaching weak models; (3) Diversity in students might help: teaching multiple students could be better than teaching one student or the teacher itself.
A Generic Method for Fine-grained Category Discovery in Natural Language Texts
To address these shortcomings, we introduce a method that successfully detects fine-grained clusters of semantically similar texts guided by a novel objective function.
Implicit Neural Representations for Robust Joint Sparse-View CT Reconstruction
Recognizing that CT often involves scanning similar subjects, we propose a novel approach to improve reconstruction quality through joint reconstruction of multiple objects using INRs.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10.
The Common Stability Mechanism behind most Self-Supervised Learning Approaches
Last couple of years have witnessed a tremendous progress in self-supervised learning (SSL), the success of which can be attributed to the introduction of useful inductive biases in the learning process to learn meaningful visual representations while avoiding collapse.
Biological Valuation Map of Flanders: A Sentinel-2 Imagery Analysis
The synergy of machine learning and satellite imagery analysis has demonstrated significant productivity in this field, as evidenced by several studies.
Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors
Proper scoring rules evaluate the quality of probabilistic predictions, playing an essential role in the pursuit of accurate and well-calibrated models.
Estimating calibration error under label shift without labels
In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems.
Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection
Despite their impressive predictive performance in various computer vision tasks, deep neural networks (DNNs) tend to make overly confident predictions, which hinders their widespread use in safety-critical applications.
Beyond Document Page Classification: Design, Datasets, and Challenges
This paper highlights the need to bring document classification benchmarking closer to real-world applications, both in the nature of data tested ($X$: multi-channel, multi-paged, multi-industry; $Y$: class distributions and label set variety) and in classification tasks considered ($f$: multi-page document, page stream, and document bundle classification, ...).
Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction
However, it is difficult for previous unsupervised methods to retain structural information from CT images while handling the non-local characteristics of metal artifacts.
Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning
Seemingly, FL can provide a degree of protection against gradient inversion attacks on weight updates, since the gradient of a single step is concealed by the accumulation of gradients over multiple local iterations.
Confidence-aware Personalized Federated Learning via Variational Expectation Maximization
A global model is introduced as a latent variable to augment the joint distribution of clients' parameters and capture the common trends of different clients, optimization is derived based on the principle of maximizing the marginal likelihood and conducted using variational expectation maximization.
Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels
As a result, we obtain superior Dice scores and model calibration, which supports the wider adoption of DMLs in practice.
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
To address this, we introduce Jaccard Metric Losses (JMLs), which are identical to the soft Jaccard loss in standard settings with hard labels but are fully compatible with soft labels.
Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data
Deep neural networks are often applied to medical images to automate the problem of medical diagnosis.
A Consistent and Differentiable Lp Canonical Calibration Error Estimator
As a remedy, we propose a low-bias, trainable calibration error estimator based on Dirichlet kernel density estimates, which asymptotically converges to the true $L_p$ calibration error.
On confidence intervals for precision matrices and the eigendecomposition of covariance matrices
Moreover, we derive a method to bound the entries of the inverse covariance matrix, the so-called precision matrix.
MRF-UNets: Searching UNet with Markov Random Fields
UNet [27] is widely used in semantic segmentation due to its simplicity and effectiveness.
Designing MacPherson Suspension Architectures using Bayesian Optimization
We show that the proposed approach is general, scalable, and efficient, and that the novel convergence criteria can be implemented straightforwardly based on existing concepts and subroutines in popular Bayesian optimization software packages.
Combinatorial optimization for low bit-width neural networks
In this paper, we explore methods of direct combinatorial optimization in the problem of risk minimization with binary weights, which can be made equivalent to a non-monotone submodular maximization under certain conditions.
On the relationship between calibrated predictors and unbiased volume estimation
This has led to a renewed focus on calibrated predictions in the medical imaging and broader machine learning communities.
Improving Differentially Private SGD via Randomly Sparsified Gradients
Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive isotropic Gaussian noise.
Calibration Regularized Training of Deep Neural Networks using Kernel Density Estimation
The computational complexity of our estimator is O(n^2), matching that of the kernel maximum mean discrepancy, used in a previously considered trainable calibration estimator.
Greedy Bayesian Posterior Approximation with Deep Ensembles
This paper proposes a novel and principled method to tackle this limitation, minimizing an $f$-divergence between the true posterior and a kernel density estimator (KDE) in a function space.
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
In this paper, we introduce two constraints that are worth consideration in designing a calibration map for post-hoc calibration.
CLIMAT: Clinically-Inspired Multi-Agent Transformers for Knee Osteoarthritis Trajectory Forecasting
We show the effectiveness of our method in predicting the development of structural knee osteoarthritis changes over time.
Deep learning on fundus images detects glaucoma beyond the optic disc
We trained and evaluated deep learning models using fundus images that underwent a certain cropping policy.
Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
We verify these results empirically in an extensive validation on six medical segmentation tasks and can confirm that metric-sensitive losses are superior to cross-entropy based loss functions in case of evaluation with Dice Score or Jaccard Index.
Additive Tree-Structured Conditional Parameter Spaces in Bayesian Optimization: A Novel Covariance Function and a Fast Implementation
Bayesian optimization (BO) is a sample-efficient global optimization algorithm for black-box functions which are expensive to evaluate.
Additive Tree-Structured Covariance Function for Conditional Parameter Spaces in Bayesian Optimization
Bayesian optimization (BO) is a sample-efficient global optimization algorithm for black-box functions which are expensive to evaluate.
Pathological myopia classification with simultaneous lesion segmentation using deep learning
This investigation reports on the results of convolutional neural networks developed for the recently introduced PathologicAL Myopia (PALM) dataset, which consists of 1200 fundus images.
AOWS: Adaptive and optimal network width search with latency constraints
We introduce a novel efficient one-shot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware.
Discriminative training of conditional random fields with probably submodular constraints
In order to constrain such a model to remain tractable, previous approaches have enforced the weight vector to be positive for pairwise potentials in which the labels differ, and set pairwise potentials to zero in the case that the label remains the same.
Adaptive Compression-based Lifelong Learning
The latter approach falls under the denomination of lifelong learning, where the model is updated in a way that it performs well on both old and new tasks, without having access to the old task's training samples anymore.
Yes, IoU loss is submodular - as a function of the mispredictions
This note is a response to [7] in which it is claimed that [13, Proposition 11] is false.
Efficient semantic image segmentation with superpixel pooling
In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation.
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses.
Towards a glaucoma risk index based on simulated hemodynamics from fundus images
In this paper we propose a first approach for characterizing those changes using computational hemodynamics.
Function Norms and Regularization in Deep Networks
Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems.
An Ensemble Deep Learning Based Approach for Red Lesion Detection in Fundus Images
In this paper we propose a novel method for red lesion detection based on combining both deep learned and domain knowledge.
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses.
Ranked #34 on
Semantic Segmentation
on PASCAL VOC 2012 test
Intraoperative margin assessment of human breast tissue in optical coherence tomography images using deep neural networks
The use of a function norm introduces a direct control over the complexity of the function with the aim of diminishing the risk of overfitting.
An Efficient Decomposition Framework for Discriminative Segmentation with Supermodular Losses
These loss functions do not necessarily have the same structure as the one used by the segmentation inference algorithm, and in general, we may have to resort to generic submodular minimization algorithms for loss augmented inference.
Slack and Margin Rescaling as Convex Extensions of Supermodular Functions
We demonstrate in this paper that we may use these concepts to define polynomial time convex extensions of arbitrary supermodular functions, providing an analysis framework for the tightness of these surrogates.
Stochastic Function Norm Regularization of Deep Networks
In this paper, we study the feasibility of directly using the $L_2$ function norm for regularization.
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
We characterize the uncertainty of differences with confidence intervals obtained using a parametric distribution on parameters of a sparse estimator.
A Test of Relative Similarity For Model Selection in Generative Models
Probabilistic generative models provide a powerful framework for representing data that avoids the expense of manual annotation typically needed by discriminative approaches.
Understanding Objects in Detail with Fine-Grained Attributes
We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object.
