Related papers: Style Blind Domain Generalized Semantic Segmentati…

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available…

Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in…

Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent advances primarily focus on pseudo-labeling, consistency…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

Deep learning based methods hold state-of-the-art results in low-level image processing tasks, but remain difficult to interpret due to their black-box construction. Unrolled optimization networks present an interpretable alternative to…

Accurate segmentation of brain images typically requires the integration of complementary information from multiple image modalities. However, clinical data for all modalities may not be available for every patient, creating a significant…

Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images…

Semi-supervised semantic segmentation (SSS) has recently gained increasing research interest as it can reduce the requirement for large-scale fully-annotated training data. The current methods often suffer from the confirmation bias from…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

Deep learning approaches to generic (non-semantic) segmentation have so far been indirect and relied on edge detection. This is in contrast to semantic segmentation, where DNNs are applied directly. We propose an alternative approach called…

Class imbalance is a critical issue in image classification that significantly affects the performance of deep recognition models. In this work, we first identify a network degeneration dilemma that hinders the model learning by introducing…

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a…

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict…

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains.…

Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of…

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we…

Due to the difficulty of obtaining labeled data for hyperspectral images (HSIs), cross-scene classification has emerged as a widely adopted approach in the remote sensing community. It involves training a model using labeled data from a…

This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated…

Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and…

Coherent noise regularly plagues seismic recordings, causing artefacts and uncertainties in products derived from down-the-line processing and imaging tasks. The outstanding capabilities of deep learning in denoising of natural and medical…