Related papers: Masked Supervised Learning for Semantic Segmentati…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…
Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of…
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…
Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and…
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base…
Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…
Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard…
Salient Span Masking (SSM) has shown itself to be an effective strategy to improve closed-book question answering performance. SSM extends general masked language model pretraining by creating additional unsupervised training sentences that…
In this work, we present a fully self-supervised framework for semantic segmentation(FS^4). A fully bootstrapped strategy for semantic segmentation, which saves efforts for the huge amount of annotation, is crucial for building customized…
Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters…
We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with extremely sparse…
Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…
Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and…
Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation…
Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware…
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentations, primarily due to unstable training. In this paper, we…
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In the realm of computer vision, pretrained vision transformers…
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…
Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation…