Related papers: Indicative Image Retrieval: Turning Blackbox Learn…

Recently, deep learning has started to play an essential role in healthcare applications, including image search in digital pathology. Despite the recent progress in computer vision, significant issues remain for image searching in…

Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must…

Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box…

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature…

While deep learning has become a key ingredient in the top performing methods for many computer vision tasks, it has failed so far to bring similar improvements to instance-level image retrieval. In this article, we argue that reasons for…

Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The fundamental roadblock faced by deep learning methods is that…

Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is…

We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained…

How can we find interpretable, domain-appropriate models of natural phenomena given some complex, raw data such as images? Can we use such models to derive scientific insight from the data? In this paper, we propose some methods for…

In this work, we introduce a deep-learning framework designed for estimating dense image correspondences. Our fully convolutional model generates dense feature maps for images, where each pixel is associated with a descriptor that can be…

Most of the traditional work on intrinsic image decomposition rely on deriving priors about scene characteristics. On the other hand, recent research use deep learning models as in-and-out black box and do not consider the well-established,…

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

In recent years, the employment of deep learning methods has led to several significant breakthroughs in artificial intelligence. Different from traditional machine learning models, deep learning-based approaches are able to extract…

Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…

The application of Deep Neural Networks for ranking in search engines may obviate the need for the extensive feature engineering common to current learning-to-rank methods. However, we show that combining simple relevance matching features…

Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images. When used for item retrieval, a query image is embedded using the…

We revisit language bottleneck models as an approach to ensuring the explainability of deep learning models for image classification. Because of inevitable information loss incurred in the step of converting images into language, the…

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess…

Image search engines rely on appropriately designed ranking features that capture various aspects of the content semantics as well as the historic popularity. In this work, we consider the role of colour in this relevance matching process.…

In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…