-
Article
Open AccessPublisher Correction: GOSS: towards generalized open-set semantic segmentation
-
Article
Open AccessGOSS: towards generalized open-set semantic segmentation
In this paper, we extend Open-set Semantic Segmentation (OSS) into a new image segmentation task called Generalized Open-set Semantic Segmentation (GOSS). Previously, with well-known OSS, the intelligent agent...
-
Article
Poincaré Kernels for Hyperbolic Representations
Embedding data in hyperbolic spaces has proven beneficial for many advanced machine learning applications. However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e.g
-
Article
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation
Deep learning has led to tremendous progress in the field of medical artificial intelligence. However, training deep-learning models usually require large amounts of annotated data. Annotating large-scale data...
-
Chapter and Conference Paper
Hybrid Window Attention Based Transformer Architecture for Brain Tumor Segmentation
As intensities of MRI volumes are inconsistent across institutes, it is essential to extract universal features of multi-modal MRIs to precisely segment brain tumors. In this concept, we propose a volumetric v...
-
Chapter and Conference Paper
L3DMC: Lifelong Learning Using Distillation via Mixed-Curvature Space
The performance of a lifelong learning (L3) model degrades when it is trained on a series of tasks, as the geometrical formation of the embedding space changes while learning novel concepts sequentially. The m...
-
Chapter and Conference Paper
EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
Reconstructing soft tissues from stereo endoscope videos is an essential prerequisite for many medical applications. Previous methods struggle to produce high-quality geometry and appearance due to their inade...
-
Chapter and Conference Paper
A Differentiable Distance Approximation for Fairer Image Classification
Naïvely trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solution...
-
Chapter and Conference Paper
Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task
This paper proposes an adversarial learning based training approach for brain tumor segmentation task. In this concept, the 3D segmentation network learns from dual reciprocal adversarial learning approaches. ...
-
Chapter and Conference Paper
Deep Laparoscopic Stereo Matching with Transformers
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection. Despite the surge, the use o...
-
Chapter and Conference Paper
A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
We propose a Transformer architecture for volumetric segmentation, a challenging task that requires kee** a complex balance in encoding local and global spatial cues, and preserving information along all axe...
-
Chapter and Conference Paper
Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning
Learning and generalizing to novel concepts with few samples (Few-Shot Learning) is still an essential challenge to real-world applications. A principle way of achieving few-shot learning is to realize a model...
-
Chapter and Conference Paper
Duo-SegNet: Adversarial Dual-Views for Semi-supervised Medical Image Segmentation
Segmentation of images is a long-standing challenge in medical AI. This is mainly due to the fact that training a neural network to perform image segmentation requires a significant number of pixel-level annot...
-
Chapter and Conference Paper
Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks. In this work, we propose a fully attentional netwo...
-
Chapter and Conference Paper
On Modulating the Gradient for Meta-learning
Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data. Our method, termed ModG...
-
Chapter and Conference Paper
Devon: Deformable Volume Network for Learning Optical Flow
We propose a new neural network module, Deformable Cost Volume, for learning large displacement optical flow. The module does not distort the original images or their feature maps and therefore avoids the arti...
-
Chapter and Conference Paper
Scalable Deep k-Subspace Clustering
Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a method that simultaneously learns ...
-
Chapter and Conference Paper
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
We study an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured in 10 distinct exhibition spaces of ...
-
Chapter
Learning Domain Invariant Embeddings by Matching Distributions
One of the characteristics of the domain problem is that the source and target data have been drawn from different distributions. A natural approach to addressing this problem therefore consists of learning ...
-
Chapter
Dictionary Learning on Grassmann Manifolds
Sparse representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models...
