Related papers: Multi-Group Proportional Representation in Retriev…
Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequences of document ID tokens. These generative retrieval models cast the retrieval problem to a document…
Representation learning is the first step in automating tasks such as research paper recommendation, classification, and retrieval. Due to the accelerating rate of research publication, together with the recognised benefits of…
Image inverse halftoning is a classic image restoration task, aiming to recover continuous-tone images from halftone images with only bilevel pixels. Because the halftone images lose much of the original image content, inverse halftoning is…
For long time, person re-identification and image search are two separately studied tasks. However, for person re-identification, the effectiveness of local features and the "query-search" mode make it well posed for image search…
We present a novel feature matching algorithm that systematically utilizes the geometric properties of features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes with the…
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent…
Automatic Gender Recognition (AGR) systems are an increasingly widespread application in the Machine Learning (ML) landscape. While these systems are typically understood as detecting gender, they often classify datapoints based on…
Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…
Multi-task learning is a popular machine learning approach that enables simultaneous learning of multiple related tasks, improving algorithmic efficiency and effectiveness. In the hard parameter sharing approach, an encoder shared through…
The analysis of large collections of image data is still a challenging problem due to the difficulty of capturing the true concepts in visual data. The similarity between images could be computed using different and possibly multimodal…
We propose a new method for analyzing a set of parameters in a multiple criteria ranking method. Unlike the existing techniques, we do not use any optimization technique, instead incorporating and extending a Segmenting Description…
Estimation of the mixing distribution under a general mixture model is a very difficult problem, especially when the mixing distribution is assumed to have a density. Predictive recursion (PR) is a fast, recursive algorithm for…
We describe our solution for the PIRM Super-Resolution Challenge 2018 where we achieved the 2nd best perceptual quality for average RMSE<=16, 5th best for RMSE<=12.5, and 7th best for RMSE<=11.5. We modify a recently proposed Multi-Grid…
The concern about hidden discrimination in machine learning models is growing, as their widespread real-world applications increasingly impact human lives. Various techniques, including commonly used group fairness measures and several…
Studies have shown that the people depicted in image search results tend to be of majority groups with respect to socially salient attributes. This skew goes beyond that which already exists in the world - e.g., Kay et al. showed that…
Person re-identification aims to identify a specific person at distinct times and locations. It is challenging because of occlusion, illumination, and viewpoint change in camera views. Recently, multi-shot person re-id task receives more…
The classical linear ordering problem seeks a single ranking representing a given preference matrix. While suitable for homogeneous populations, it fails when observed preferences arise from several latent groups with distinct ranking…
Imbalanced classification presents a formidable challenge in machine learning, particularly when tabular datasets are plagued by noise and overlapping class boundaries. From a geometric perspective, the core difficulty lies in the…
Images are often termed as representations of perceived reality. As such, racial and gender biases in popular culture and visual media could play a critical role in shaping people's perceptions of society. While previous research has made…
Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…