Related papers: Generating Hard Examples for Pixel-wise Classifica…

Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work. E-PixelHop consists of the…

Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods. The latest research shows that…

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference…

Referring Expression Comprehension (REC) aims to identify a particular object in a scene by a natural language expression, and is an important topic in visual language understanding. State-of-the-art methods for this task are based on deep…

With large numbers of transients discovered by current and future imaging surveys, machine learning is increasingly applied to light curve and host galaxy properties to select events for follow-up. However, finding rare types of transients…

The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing…

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention.…

The absence of large scale datasets with pixel-level supervisions is a significant obstacle for the training of deep convolutional networks for scene text segmentation. For this reason, synthetic data generation is normally employed to…

Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…

Satellites equipped with optical sensors capture high-resolution imagery, providing valuable insights into various environmental phenomena. In recent years, there has been a surge of research focused on addressing some challenges in remote…

Weakly supervised image segmentation with image-level labels has drawn attention due to the high cost of pixel-level annotations. Traditional methods using Class Activation Maps (CAMs) often highlight only the most discriminative regions,…

Grouping images into semantically meaningful categories using low-level visual feature is a challenging and important problem in content-based image retrieval. The groupings can be used to build effective indices for an image database.…

The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented. In many hyperspectral target detection problems, acquiring accurately labeled training data is…

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation…

This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures. We develop supervised convolutional architectures for discriminating signals in…

This paper proposes a novel method of classifying malware into families using high-resolution greyscale images and multiple instance learning to overcome adversarial binary enlargement. Current methods of visualisation-based malware…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for…