Related papers: Continual Attentive Fusion for Incremental Learnin…
Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive…
Interactive segmentation, an integration of AI algorithms and human expertise, premises to improve the accuracy and efficiency of curating large-scale, detailed-annotated datasets in healthcare. Human experts revise the annotations…
Class incremental learning aims to enable models to learn from sequential, non-stationary data streams across different tasks without catastrophic forgetting. In class incremental semantic segmentation (CISS), the semantic content of image…
The 3D scene understanding is mainly considered as a crucial requirement in computer vision and robotics applications. One of the high-level tasks in 3D scene understanding is semantic segmentation of RGB-Depth images. With the availability…
Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…
Few-shot segmentation focuses on the generalization of models to segment unseen object with limited annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query…
Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…
Researchers have long tried to minimize training costs in deep learning while maintaining strong generalization across diverse datasets. Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic…
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical…
Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…
The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the current data distribution to the detriment of the past…
Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…
In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…
The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose…
Continual learning has been a major problem in the deep learning community, where the main challenge is how to effectively learn a series of newly arriving tasks without forgetting the knowledge of previous tasks. Initiated by Learning…
Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric…
The expansion of neural network sizes and the enhanced resolution of modern image sensors result in heightened memory and power demands to process modern computer vision models. In order to deploy these models in extremely…
Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…
Referring image segmentation (RIS) requires accurate segmentation of target regions in images according to language descriptions, which is a cross-modal task integrating vision and language. Existing RIS methods typically employ large-scale…