Related papers: ReplaceBlock: An improved regularization method ba…

For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation…

An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the…

The goal of object detection is to find objects in an image. An object detector accepts an image and produces a list of locations as $(x,y)$ pairs. Here we introduce a new concept: {\bf location-based boosting}. Location-based boosting…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

In this paper, we study the problem of recovering a sharp version of a given blurry image when the blur kernel is unknown. Previous methods often introduce an image-independent regularizer (such as Gaussian or sparse priors) on the desired…

Node classification is an important task to solve in graph-based learning. Even though a lot of work has been done in this field, imbalance is neglected. Real-world data is not perfect, and is imbalanced in representations most of the…

The goal of dynamic scene deblurring is to remove the motion blur in a given image. Typical learning-based approaches implement their solutions by minimizing the L1 or L2 distance between the output and the reference sharp image. Recent…

Image restoration is a low-level vision task which is to restore degraded images to noise-free images. With the success of deep neural networks, the convolutional neural networks surpass the traditional restoration methods and become the…

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…

In the anomaly detection setting, the native feature embedding can be a crucial source of bias. We present a technique, Feature Omission using Context in Unsupervised Settings (FOCUS) to learn a feature mapping that is invariant to changes…

As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain,…

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic…

Machine unlearning is an emerging technology that has come to attract widespread attention. A number of factors, including regulations and laws, privacy, and usability concerns, have resulted in this need to allow a trained model to forget…

Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. However, such a strategy raises one key problem that attention regions will gradually…

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera. Our method leverages motion…

Deblurring is the task of restoring a blurred image to a sharp one, retrieving the information lost due to the blur. In blind deblurring we have no information regarding the blur kernel. As deblurring can be considered as an image to image…

Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…

In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual. However, in a crowded scene, off-shelf-detectors may generate bounding boxes involving multiple people, where the large…

Localizing objects in an unsupervised manner poses significant challenges due to the absence of key visual information such as the appearance, type and number of objects, as well as the lack of labeled object classes typically available in…

While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and…