Related papers: Rethinking Query-based Transformer for Continual I…
2D images and 3D point clouds are foundational data types for multimedia applications, including real-time video analysis, augmented reality (AR), and 3D scene understanding. Class-incremental semantic segmentation (CSS) requires…
For complex segmentation tasks, the achievable accuracy of fully automated systems is inherently limited. Specifically, when a precise segmentation result is desired for a small amount of given data sets, semi-automatic methods exhibit a…
Annotation of medical images, such as MRI and CT scans, is crucial for evaluating treatment efficacy and planning radiotherapy. However, the extensive workload of medical professionals limits their ability to annotate large image datasets,…
This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While class-incremental…
Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent…
The goal of interactive image segmentation is to delineate specific regions within an image via visual or language prompts. Low-latency and high-quality interactive segmentation with diverse prompts remain challenging for existing…
Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to…
With the development of underwater exploration and marine protection, underwater vision tasks are widespread. Due to the degraded underwater environment, characterized by color distortion, low contrast, and blurring, camouflaged instance…
Referring image segmentation (RIS) aims to find a segmentation mask given a referring expression grounded to a region of the input image. Collecting labelled datasets for this task, however, is notoriously costly and labor-intensive. To…
In this paper, we propose a simple yet efficientinstance segmentation approach based on the single-stage anchor-free detector, termed SAIS. In our approach, the instancesegmentation task consists of two parallel subtasks which re-spectively…
The two main challenges faced by continual learning approaches are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains…
Semantic image synthesis (SIS) refers to the problem of generating realistic imagery given a semantic segmentation mask that defines the spatial layout of object classes. Most of the approaches in the literature, other than the quality of…
Medical image registration is a fundamental task in medical image analysis, aiming to establish spatial correspondences between paired images. However, existing unsupervised deformable registration methods rely solely on intensity-based…
Class Incremental Semantic Segmentation~(CISS), within Incremental Learning for semantic segmentation, targets segmenting new categories while reducing the catastrophic forgetting on the old categories.Besides, background shifting, where…
The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains autoencoders with Neural…
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed…
Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven…
Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a…