Sima Behpour
YOU?
Author Swipe
View article: Open Ad-hoc Categorization with Contextualized Feature Learning
Open Ad-hoc Categorization with Contextualized Feature Learning Open
Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories are created dynamically to serve specific goals. We study open ad-hoc cat…
View article: USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation
USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation Open
The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment Anythi…
View article: Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection Open
Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tas…
View article: A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets Open
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting. The rise of Vision-Language models (VLMs) has unlocked numerous application…
View article: GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients Open
Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient …
View article: UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models Open
In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited annotat…
View article: Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection Open
Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tas…
View article: Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization
Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization Open
Motivation Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules…
View article: Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations
Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations Open
We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images. Unlike most existing methods that require voxel-wise densely labeled training data, our weakly-supervised CIVA-Net is the first model that onl…
View article: Active Learning in Video Tracking
Active Learning in Video Tracking Open
Active learning methods, like uncertainty sampling, combined with probabilistic prediction techniques have achieved success in various problems like image classification and text classification. For more complex multivariate prediction tas…
View article: Consistent Robust Adversarial Prediction for General Multiclass Classification
Consistent Robust Adversarial Prediction for General Multiclass Classification Open
We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case condi…
View article: Adversarial Structural Learning: Approximating Training Data for Multi-Variate Predictions
Adversarial Structural Learning: Approximating Training Data for Multi-Variate Predictions Open
In this thesis, we address two important characteristics of prediction tasks in many real world problems\nby developing an adversarial classification framework. Structured data is the feature of many real\nworld applications (e.g., compute…
View article: ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-Label Classification
ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-Label Classification Open
Many structured prediction tasks arising in computer vision and natural language processing tractably reduce to making minimum cost cuts in graphs with edge weights learned using maximum margin methods. Unfortunately, the hinge loss used t…
View article: ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection
ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection Open
The use of random perturbations of ground truth data, such as random translation or scaling of bounding boxes, is a common heuristic used for data augmentation that has been shown to prevent overfitting and improve generalization. Since th…