150 citations · 186 across the 32 of their papers we have counts for
33 papers
Task Switching Without Forgetting via Proximal Decoupling
Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger +2
In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off through regularization, penali…
Multi-Domain Learning with Global Expert Mapping
Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou +3
Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset learning, where a single mo…
HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images
Pourya Shamsolmoali, Masoumeh Zareapoor, Michael Felsberg +3
Despite advances in object detection, aerial imagery remains a challenging domain, as models often fail to generalize across variations in spatial resolution, scene composition, an…
Selective Prediction Forgetting for Adaptation of Weakly Supervised Localization of Histology Images
Alexis Guichemerre, Banafsheh Karimian, Soufiane Belharbi +6
Under strong cross-domain shifts, weakly supervised object localization (WSOL) models often lose their capacity to discriminate and develop a strong prediction bias toward a subset…
IntRec: Intent-based Retrieval with Contrastive Refinement
Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger +1
Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects. Existing open-vocabular…
Finding Structure in Continual Learning
Pourya Shamsolmoali, Masoumeh Zareapoor
Learning from a stream of tasks usually pits plasticity against stability: acquiring new knowledge often causes catastrophic forgetting of past information. Most methods address th…
From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou +3
Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have…
HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
Sharanya Dasgupta, Sujoy Nath, Arkaprabha Basu +2
Large Language Models (LLMs) have recently garnered widespread attention due to their adeptness at generating innovative responses to the given prompts across a multitude of domain…
Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI
Mahdi Alehdaghi, Rajarshi Bhattacharya, Pourya Shamsolmoali +3
As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited in…
Fractional Correspondence Framework in Detection Transformer
Masoumeh Zareapoor, Pourya Shamsolmoali, Huiyu Zhou +2
The Detection Transformer (DETR), by incorporating the Hungarian algorithm, has significantly simplified the matching process in object detection tasks. This algorithm facilitates…
From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification
Mahdi Alehdaghi, Rajarshi Bhattacharya, Pourya Shamsolmoali +2
Visible-infrared person re-identification (VI-ReID) aims to match individuals across different camera modalities, a critical task in modern surveillance systems. While current VI-R…
TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel Conditioning
Tsiry Mayet, Pourya Shamsolmoali, Simon Bernard +3
Diffusion models have emerged as highly effective techniques for inpainting, however, they remain constrained by slow sampling rates. While recent advances have enhanced generation…
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
Alexis Guichemerre, Soufiane Belharbi, Tsiry Mayet +4
Given the emergence of deep learning, digital pathology has gained popularity for cancer diagnosis based on histology images. Deep weakly supervised object localization (WSOL) mode…
Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification
Mahdi Alehdaghi, Pourya Shamsolmoali, Rafael M. O. Cruz +1
A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modaliti…
SeTformer is What You Need for Vision and Language
Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger +1
The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibi…
Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation
Pourya Shamsolmoali, Jocelyn Chanussot, Huiyu Zhou +1
Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their dep…
Distance Weighted Trans Network for Image Completion
Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou +2
The challenge of image generation has been effectively modeled as a problem of structure priors or transformation. However, existing models have unsatisfactory performance in under…
ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer
Yifan Xu, Pourya Shamsolmoali, Jie Yang
Visual place recognition (VPR) is a highly challenging task that has a wide range of applications, including robot navigation and self-driving vehicles. VPR is particularly difficu…
Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold
Pourya Shamsolmoali, Masoumeh Zareapoor
This paper focuses on an accurate and fast interpolation approach for image transformation employed in the design of CNN architectures. Standard Spatial Transformer Networks (STNs)…
Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification
Mahdi Alehdaghi, Arthur Josi, Pourya Shamsolmoali +2
Visible-infrared person re-identification seeks to retrieve images of the same individual captured over a distributed network of RGB and IR sensors. Several V-I ReID approaches dir…
Image Completion via Dual-path Cooperative Filtering
Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger
Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress. However, state-of-art methods typically provide poor cross…
VTAE: Variational Transformer Autoencoder with Manifolds Learning
Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou +2
Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a nonlinear fun…
Hybrid Gromov-Wasserstein Embedding for Capsule Learning
Pourya Shamsolmoali, Masoumeh Zareapoor, Swagatam Das +2
Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchica…
Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images
Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger +2
Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detec…