相关论文: Extending Class Activation Mapping Using Gaussian …

The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature…

Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Deep Learning approaches for real, large, and complex scientific data sets can be very challenging to design. In this work, we present a complete search for a finely-tuned and efficiently scaled deep learning classifier to identify usable…

Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM)…

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of…

Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However, these models often struggle to represent high-frequency…

Leveraging spatiotemporal information in videos is critical for weakly supervised video object localization (WSVOL) tasks. However, state-of-the-art methods only rely on visual and motion cues, while discarding discriminative information,…

Semantic segmentation architectures are mainly built upon an encoder-decoder structure. These models perform subsequent downsampling operations in the encoder. Since operations on high-resolution activation maps are computationally…

Accurate segmentation of the fetal brain from Magnetic Resonance Image (MRI) is important for prenatal assessment of fetal development. Although deep learning has shown the potential to achieve this task, it requires a large fine annotated…

Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations. However, they are also known for their limited modeling…

We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent…

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy…

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…

We present an improved model for MRF-based depth upsampling, guided by image- as well as 3D surface normal features. By exploiting the underlying camera model we define a novel regularization term that implicitly evaluates the planarity of…

Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we…

Learning powerful discriminative features for remote sensing image scene classification is a challenging computer vision problem. In the past, most classification approaches were based on handcrafted features. However, most recent…

Deep Active Learning (DAL) has been advocated as a promising method to reduce labeling costs in supervised learning. However, existing evaluations of DAL methods are based on different settings, and their results are controversial. To…

We study how to evaluate the quantitative information content of a region within an image for a particular label. To this end, we bridge class activation maps with information theory. We develop an informative class activation map…

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…