相关论文: A New Benchmark and Progress Toward Improved Weakl…

The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that…

Modern image retrieval systems increasingly rely on the use of deep neural networks to learn embedding spaces in which distance encodes the relevance between a given query and image. In this setting, existing approaches tend to emphasize…

We investigated how the application of deep learning, specifically the use of convolutional networks trained with GPUs, can help to build better predictive models in telecommunication business environments, and fill this gap. In particular,…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent WSSS methods, we identify that introducing weak labels with…

Deep neural networks have become a foundational tool for addressing imaging inverse problems. They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover. However,…

Precise breast cancer classification on histopathological images has the potential to greatly improve the diagnosis and patient outcome in oncology. The data imbalance problem largely stems from the inherent imbalance within medical image…

The implementation of deep learning based computer aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model…

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple…

Unpaired 3D object completion aims to predict a complete 3D shape from an incomplete input without knowing the correspondence between the complete and incomplete shapes. In this paper, we propose the novel KTNet to solve this task from the…

Classification-regression prediction networks have realized impressive success in several modern deep trackers. However, there is an inherent difference between classification and regression tasks, so they have diverse even opposite demands…

Deep learning has revolutionized modern data science. However, how to accurately quantify the uncertainty of predictions from large-scale deep neural networks (DNNs) remains an unresolved issue. To address this issue, we introduce a novel…

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective, we first propose a…

Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This…

Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks. This…

We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees. Our calibration algorithms work with any underlying model and (unknown) data-generating…

We study a model of machine teaching where the teacher mapping is constructed from a size function on both concepts and examples. The main question in machine teaching is the minimum number of examples needed for any concept, the so-called…

This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic…

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…