Related papers: Deep Supervision with Intermediate Concepts
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the…
We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…
Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate superpixels and…
While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult…
In image classification task, feature extraction is always a big issue. Intra-class variability increases the difficulty in designing the extractors. Furthermore, hand-crafted feature extractor cannot simply adapt new situation. Recently,…
Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…
Superpixels are higher-order perceptual groups of pixels in an image, often carrying much more information than the raw pixels. There is an inherent relational structure to the relationship among different superpixels of an image such as…
Deep convolutional neural networks (CNNs) are state-of-the-art for semantic image segmentation, but typically require many labeled training samples. Obtaining 3D segmentations of medical images for supervised training is difficult and labor…
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…
The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require…
Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them…
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs…
Convolutional Neural Networks (CNNs) have become the state of the art method for image classification in the last ten years. Despite the fact that they achieve superhuman classification accuracy on many popular datasets, they often perform…
Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep…
Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…
Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…
Nowadays, deep learning can be employed to a wide ranges of fields including medicine, engineering, etc. In deep learning, Convolutional Neural Network (CNN) is extensively used in the pattern and sequence recognition, video analysis,…
Deep learning techniques have been successfully used in learning a common representation for multi-view data, wherein the different modalities are projected onto a common subspace. In a broader perspective, the techniques used to…
In this work we address the problem of indoor scene understanding from RGB-D images. Specifically, we propose to find instances of common furniture classes, their spatial extent, and their pose with respect to generalized class models. To…
Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep…