Related papers: PICASO: Permutation-Invariant Cascaded Attentional…
In real-world applications of image recognition tasks, such as human pose estimation, cameras often capture objects, like human bodies, at low resolutions. This scenario poses a challenge in extracting and leveraging multi-scale features,…
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…
Visual attention mechanisms are a key component of neural network models for computer vision. By focusing on a discrete set of objects or image regions, these mechanisms identify the most relevant features and use them to build more…
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle variations among highly-confused categories. Most existing…
Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is…
Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA)…
The field of view (FOV) of convolutional neural networks is highly related to the accuracy of inference. Dilated convolutions are known as an effective solution to the problems which require large FOVs. However, for general-purpose hardware…
Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that…
Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant. However, the blur involved in real applications are usually space-variant due to object motion, out-of-focus, etc., resulting…
Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it. In this work, a novel lightweight and effective attention method named…
Within (semi-)automated visual inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The…
Although deep convolutional networks have been widely studied for head and neck (HN) organs at risk (OAR) segmentation, their use for routine clinical treatment planning is limited by a lack of robustness to imaging artifacts, low soft…
The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsupervised training of aggregation functions in graph neural…
Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…
Few-shot anomaly detection (FSAD) denotes the identification of anomalies within a target category with a limited number of normal samples. Existing FSAD methods largely rely on pre-trained feature representations to detect anomalies, but…
We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images.…
Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…
In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited…
Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end…
Graphical LASSO (GLASSO) is a widely used method for estimating sparse precision matrices and learning undirected graphical models in high-dimensional settings. Because GLASSO penalizes entries of the precision matrix directly, however, it…