Related papers: Triple-View Knowledge Distillation for Semi-Superv…
Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by…
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…
Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised…
The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the…
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
Reviewing plays an important role when learning knowledge. The knowledge acquisition at a certain time point may be strongly inspired with the help of previous experience. Thus the knowledge growing procedure should show strong relationship…
Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks.…
Current knowledge distillation (KD) methods for semantic segmentation focus on guiding the student to imitate the teacher's knowledge within homogeneous architectures. However, these methods overlook the diverse knowledge contained in…
Sound event detection (SED) is essential for recognizing specific sounds and their temporal locations within acoustic signals. This becomes challenging particularly for on-device applications, where computational resources are limited. To…
Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…
Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not…
Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill…
We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii)…
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations. Contrary to existing approaches posing semantic segmentation as a single task of region-based classification, our…
Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…
Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and…
The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exploiting unlabeled examples in the learning process. In this…