Related papers: Deformable Classifiers
Object recognition is an essential capability when performing various tasks. Humans naturally use either or both visual and tactile perception to extract object class and properties. Typical approaches for robots, however, require complex…
Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…
In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We enforce feature space invariances using a novel layer based on invariant integration. This allows us to…
Object pose estimation is a long-standing problem in computer vision. Recently, attention-based vision transformer models have achieved state-of-the-art results in many computer vision applications. Exploiting the permutation-invariant…
We propose a novel deep learning framework based on Vision Transformers (ViT) for one-class classification. The core idea is to use zero-centered Gaussian noise as a pseudo-negative class for latent space representation and then train the…
Deep neural networks for image classification typically consists of a convolutional feature extractor followed by a fully connected classifier network. The predicted and the ground truth labels are represented as one hot vectors. Such a…
Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the…
Place recognition is one of the most challenging problems in computer vision, and has become a key part in mobile robotics and autonomous driving applications for performing loop closure in visual SLAM systems. Moreover, the difficulty of…
Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or the variation…
Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior information is a…
We develop a learning framework for building deformable templates, which play a fundamental role in many image analysis and computational anatomy tasks. Conventional methods for template creation and image alignment to the template have…
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…
Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extract…
Grasping deformable objects is not well researched due to the complexity in modelling and simulating the dynamic behavior of such objects. However, with the rapid development of physics-based simulators that support soft bodies, the…
Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for…
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…