Related papers: Class Incremental Medical Image Segmentation via P…

Class-Incremental Semantic Segmentation (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes. By abstracting mainstream methods into two stages (visual feature extraction and…

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation…

The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, privacy violations, and trust erosion in digital media.…

Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefore necessary, but compact 3D encoders tend to lose fine structural cues (small lesions…

Multi-modality medical imaging is crucial in clinical treatment as it can provide complementary information for medical image segmentation. However, collecting multi-modal data in clinical is difficult due to the limitation of the scan time…

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes. Previous work has introduced generative replay, which involves replaying old class samples generated…

Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption…

High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands)…

Missing modalities pose a major issue in Alzheimer's Disease (AD) diagnosis, as many subjects lack full imaging data due to cost and clinical constraints. While multi-modal learning leverages complementary information, most existing methods…

Polyp segmentation, a contentious issue in medical imaging, has seen numerous proposed methods aimed at improving the quality of segmented masks. While current state-of-the-art techniques yield impressive results, the size and computational…

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of…

Many medical image segmentation methods have achieved impressive results. Yet, most existing methods do not take into account the shape-intensity prior information. This may lead to implausible segmentation results, in particular for images…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously…

The limited availability of labeled data has driven advancements in semi-supervised learning for medical image segmentation. Modern large-scale models tailored for general segmentation, such as the Segment Anything Model (SAM), have…

Classifying pill categories from real-world images is crucial for various smart healthcare applications. Although existing approaches in image classification might achieve a good performance on fixed pill categories, they fail to handle…

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic…

Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set. Toward…

Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot…