相关论文: VLCD: Vision-Language Contrastive Distillation for…

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher…

This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the…

Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due…

Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…

Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial…

Training vision-language models (VLMs) for complex reasoning remains a challenging task, i.a. due to the scarcity of high-quality image-text reasoning data. Conversely, text-based reasoning resources are abundant and scalable, but it is…

Text-to-3D generation based on score distillation of pre-trained 2D diffusion models has gained increasing interest, with variational score distillation (VSD) as a remarkable example. VSD proves that vanilla score distillation can be…

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

While large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents, they still suffer from hallucinations, where the generated text inaccurately reflects…

Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to the scarcity of labeled data in the medical domain. By leveraging paired/unpaired vision and text datasets through self-supervised learning, models…

Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hold great potential for clinical reasoning, their high computational and memory requirements…

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model…

Vision-Language Models (VLMs) have shown remarkable capabilities in a large number of downstream tasks. Nonetheless, compositional image understanding remains a rather difficult task due to the object bias present in training data. In this…

Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approaches leverage…

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher…

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…

Computational Pathology (CPATH) systems have the potential to automate diagnostic tasks. However, the artifacts on the digitized histological glass slides, known as Whole Slide Images (WSIs), may hamper the overall performance of CPATH…

The role of data in building AI systems has recently been emphasized by the emerging concept of data-centric AI. Unfortunately, in the real-world, datasets may contain dirty samples, such as poisoned samples from backdoor attack, noisy…