Related papers: Discriminate-and-Rectify Encoders: Learning from I…

Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised…

Self-supervised learning converts raw perceptual data such as images to a compact space where simple Euclidean distances measure meaningful variations in data. In this paper, we extend this formulation by adding additional geometric…

Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruction-based learning (e.g., BEiT, SimMIM, MAE) are the two leading paradigms for self-supervised learning of vision transformers, but they differ substantially in their…

Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…

Spatial perception aims to estimate camera motion and scene structure from visual observations, a problem traditionally addressed through geometric modeling and physical consistency constraints. Recent learning-based methods have…

In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate…

Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real…

Complex visual scenes that are composed of multiple objects, each with attributes, such as object name, location, pose, color, etc., are challenging to describe in order to train neural networks. Usually,deep learning networks are trained…

The high complexity of various inverse problems poses a significant challenge to model-based reconstruction schemes, which in such situations often reach their limits. At the same time, we witness an exceptional success of data-based…

In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…

Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space.…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data. However, most work in this direction requires multi-view images for each object instance as training…

Adaptive sparse coding methods learn a possibly overcomplete set of basis functions, such that natural image patches can be reconstructed by linearly combining a small subset of these bases. The applicability of these methods to visual…

Object Transfiguration replaces an object in an image with another object from a second image. For example it can perform tasks like "putting exactly those eyeglasses from image A on the nose of the person in image B". Usage of exemplar…

Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are…

Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning.…

Object pose increases intraclass object variance which makes object recognition from 2D images harder. To render a classifier robust to pose variations, most deep neural networks try to eliminate the influence of pose by using large…