Related papers: GSTO: Gated Scale-Transfer Operation for Multi-Sca…
Unsupervised domain adaptation aims to train a classification model from the labeled source domain for the unlabeled target domain. Since the data distributions of the two domains are different, the model often performs poorly on the target…
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes. This method enjoys the benefits of two novel techniques. The first one is semantic transfer (ST), which is: (1) a formulation to integrate…
Performance of neural network models relies on the availability of large datasets with minimal levels of uncertainty. Transfer Learning (TL) models have been proposed to resolve the issue of small dataset size by letting the model train on…
Achieving a universally high accuracy in object detection is quite challenging, and the mainstream focus in the industry currently lies on detecting specific classes of objects. However, deploying one or multiple object detection networks…
Feature pyramids have been proven powerful in image understanding tasks that require multi-scale features. State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using…
This paper presents a semi-supervised learning framework for a customized semantic segmentation task using multiview image streams. A key challenge of the customized task lies in the limited accessibility of the labeled data due to the…
Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a…
Due to the high diversity of image styles, the scalability to various styles plays a critical role in real-world applications. To accommodate a large amount of styles, previous multi-style transfer approaches rely on enlarging the model…
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…
Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using…
Despite the notable success of graph convolutional networks (GCNs) in skeleton-based action recognition, their performance often depends on large volumes of labeled data, which are frequently scarce in practical settings. To address this…
Graph Neural Networks (GNNs) have received a lot of interest in the recent times. From the early spectral architectures that could only operate on undirected graphs per a transductive learning paradigm to the current state of the art…
Constructing transferable descriptors for conformation representation of molecular and biological systems finds numerous applications in drug discovery, learning-based molecular dynamics, and protein mechanism analysis. Geometric graph…
Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra…
Recently, learning to hash has been widely studied for image retrieval thanks to the computation and storage efficiency of binary codes. For most existing learning to hash methods, sufficient training images are required and used to learn…
Graph neural networks (GNNs) have been predominantly driven by message-passing, where node representations are iteratively updated via local neighborhood aggregation. Despite their success, message-passing suffers from fundamental…
It has become a popular paradigm to transfer the knowledge of large-scale pre-trained models to various downstream tasks via fine-tuning the entire model parameters. However, with the growth of model scale and the rising number of…
The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported…
Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial…
Image Segmentation is a technique of partitioning the original image into some distinct classes. Many possible solutions may be available for segmenting an image into a certain number of classes, each one having different quality of…