Search Results for author:
Found 18 papers, 7 papers with code
Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning
Building upon this insight, we incorporate visual bias caused by compositions into the classifier's training and inference by estimating it as a proximate class prior.
Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
In this work, we present an approach to extract multiple representative sub-regions from a given support medical image, enabling fine-grained selection over the generated image regions.
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
First, a subdivision strategy is introduced to produce a collection of regional prototypes from the foreground of the support prototype.
Push the Boundary of SAM: A Pseudo-label Correction Framework for Medical Segmentation
One key advantage of our model is its ability to train deep networks using SAM-generated pseudo labels without relying on a set of expert-level annotations while attaining good segmentation performance.
Estimate-Then-Optimize versus Integrated-Estimation-Optimization versus Sample Average Approximation: A Stochastic Dominance Perspective
In this paper, we show that a reverse behavior appears when the model class is well-specified and there is sufficient data.
Evolutionary Generalized Zero-Shot Learning
In this work, we propose a novel Evolutionary Generalized Zero-Shot Learning setting, which (i) avoids the domain shift problem in inductive GZSL, and (ii) is more in line with the needs of real-world deployments than transductive GZSL.
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects.
Weighted Contrastive Hashing
The development of unsupervised hashing is advanced by the recent popular contrastive learning paradigm.
Cardiac Adipose Tissue Segmentation via Image-Level Annotations
To lessen the need for pixel-wise labeling, we develop a two-stage deep learning framework for cardiac adipose tissue segmentation using image-level annotations on OCT images of human cardiac substrates.
Evaluating Aleatoric Uncertainty via Conditional Generative Models
To overcome these restrictions, we study conditional generative models for aleatoric uncertainty estimation.
Zero-Shot Logit Adjustment
As a consequence of our derivation, the aforementioned two properties are incorporated into the classifier training as seen-unseen priors via logit adjustment.
Ranked #1 on
Generalized Zero-Shot Learning
on AwA2
(Accuracy Unseen metric)
Deconstructed Generation-Based Zero-Shot Model
Recent research on Generalized Zero-Shot Learning (GZSL) has focused primarily on generation-based methods.
Learning to Hash Naturally Sorts
In this paper, we tackle this problem by introducing Naturally-Sorted Hashing (NSH).
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features.
Quantifying Epistemic Uncertainty in Deep Learning
Uncertainty quantification is at the core of the reliability and robustness of machine learning.
Learning Prediction Intervals for Regression: Generalization and Calibration
We study the generation of prediction intervals in regression for uncertainty quantification.
Co-Seg: An Image Segmentation Framework Against Label Corruption
Supervised deep learning performance is heavily tied to the availability of high-quality labels for training.
Conditional Coverage Estimation for High-quality Prediction Intervals
Deep learning has achieved state-of-the-art performance to generate high-quality prediction intervals (PIs) for uncertainty quantification in regression tasks.
