Related papers: 1st Place Solution in Google Universal Images Embe…
We introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components. First, we regress pixels into a hyper-spherical embedding space so…
Extracting context from visual representations is of utmost importance in the advancement of Computer Science. Representation of such a format in Natural Language has a huge variety of applications such as helping the visually impaired etc.…
We present our solutions to the Google Landmark Challenges 2021, for both the retrieval and the recognition tracks. Both solutions are ensembles of transformers and ConvNet models based on Sub-center ArcFace with dynamic margins. Since the…
Image retrieval is a fundamental task in computer vision. Despite recent advances in this field, many techniques have been evaluated on a limited number of domains, with a small number of instance categories. Notably, most existing works…
In recent years, we have witnessed the proliferation of knowledge graphs (KG) in various domains, aiming to support applications like question answering, recommendations, etc. A frequent task when integrating knowledge from different KGs is…
Medical images are often acquired in different settings, requiring harmonization to adapt to the operating point of algorithms. Specifically, to standardize the physical spacing of imaging voxels in heterogeneous inference settings, images…
Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a…
We propose an efficient pipeline for large-scale landmark image retrieval that addresses the diversity of the dataset through two-stage discriminative re-ranking. Our approach is based on embedding the images in a feature-space using a…
Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal…
Many mathematical imaging problems are posed as non-convex optimization problems. When numerically tractable global optimization procedures are not available, one is often interested in testing ex post facto whether or not a locally…
Modern image retrieval methods typically rely on fine-tuning pre-trained encoders to extract image-level descriptors. However, the most widely used models are pre-trained on ImageNet-1K with limited classes. The pre-trained feature…
In recent years, deep learning has become a very active research tool which is used in many image processing fields. In this paper, we propose an effective image fusion method using a deep learning framework to generate a single image which…
This research explores the realm of neural image captioning using deep learning models. The study investigates the performance of different neural architecture configurations, focusing on the inject architecture, and proposes a novel…
We discuss two potentially challenging problems faced by the ecommerce industry. One relates to the problem faced by sellers while uploading pictures of products on the platform for sale and the consequent manual tagging involved. It gives…
In recent years, product categorisation has been a common issue for E-commerce companies who have utilised machine learning to categorise their products automatically. In this study, we propose an ensemble approach, using a combination of…
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…
Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep…
Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric…
Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies. The idea of ensemble learning is to assemble diverse models or multiple predictions and, thus, boost prediction…