Related papers: Boosting Occluded Image Classification via Subspac…

Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging receptive fields and reducing interference when aggregating…

Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Object occlusion boundary detection is a fundamental and crucial research problem in computer vision. This is challenging to solve as encountering the extreme boundary/non-boundary class imbalance during training an object occlusion…

Over the last two decades, deep learning has transformed the field of computer vision. Deep convolutional networks were successfully applied to learn different vision tasks such as image classification, image segmentation, object detection…

Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional feature maps. However, pairwise correlation will…

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning.…

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…

In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested on occluded images. The motivation is that there are…

Deep convolutional neural networks (DCNNs) are powerful models that yield impressive results at object classification. However, recent work has shown that they do not generalize well to partially occluded objects and to mask attacks. In…

Recognizing the expressions of partially occluded faces is a challenging computer vision problem. Previous expression recognition methods, either overlooked this issue or resolved it using extreme assumptions. Motivated by the fact that the…

This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, for which the blur estimate is ambiguous) from edges that lie…

Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited robustness to partial…

Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering…

Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the…

The crux of resolving fine-grained visual classification (FGVC) lies in capturing discriminative and class-specific cues that correspond to subtle visual characteristics. Recently, frequency decomposition/transform based approaches have…

By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions…

RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC). SSC…

Deep clustering has recently emerged as a promising technique for complex data clustering. Despite the considerable progress, previous deep clustering works mostly build or learn the final clustering by only utilizing a single layer of…