Related papers: A unified framework of predicting binary interesti…

Relevance and diversity are both crucial criteria for an effective search system. In this paper, we propose a unified learning framework for simultaneously optimizing both relevance and diversity. Specifically, the problem is formalized as…

Face Recognition (FR) has been the interest to several researchers over the past few decades due to its passive nature of biometric authentication. Despite high accuracy achieved by face recognition algorithms under controlled conditions,…

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current…

Due to the rapid advancements of sensory and computing technology, multi-modal data sources that represent the same pattern or phenomenon have attracted growing attention. As a result, finding means to explore useful information from these…

Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a limited view. We propose the Triangle of Similarity, a framework that…

Effective image deblurring typically relies on large and fully paired datasets of blurred and corresponding sharp images. However, obtaining such accurately aligned data in the real world poses a number of difficulties, limiting the…

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…

Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection. Most of these methods are based on multiple models or are…

Multiple-choice question answering (MCQA) becomes particularly challenging when all choices are relevant to the question and are semantically similar. Yet this setting of MCQA can potentially provide valuable clues for choosing the right…

In classical canonical correlation analysis (CCA), the goal is to determine the linear transformations of two random vectors into two new random variables that are most strongly correlated. Canonical variables are pairs of these new random…

Kernel alignment measures the degree of similarity between two kernels. In this paper, inspired from kernel alignment, we propose a new Linear Discriminant Analysis (LDA) formulation, kernel alignment LDA (kaLDA). We first define two…

Over the past few years, Multi-Kernel Learning (MKL) has received significant attention among data-driven feature selection techniques in the context of kernel-based learning. MKL formulations have been devised and solved for a broad…

We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. Our model solves the deblurring problem by dividing it into two successive tasks: (1) blur kernel estimation and (2) sharp image…

Inducing point Gaussian process approximations are often considered a gold standard in uncertainty estimation since they retain many of the properties of the exact GP and scale to large datasets. A major drawback is that they have…

Web image datasets curated online inherently contain ambiguous in-distribution (ID) instances and out-of-distribution (OOD) instances, which we collectively call non-conforming (NC) instances. In many recent approaches for mitigating the…

Multiple kernel learning (MKL) method is generally believed to perform better than single kernel method. However, some empirical studies show that this is not always true: the combination of multiple kernels may even yield an even worse…

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary…

Activity recognition from first-person (ego-centric) videos has recently gained attention due to the increasing ubiquity of the wearable cameras. There has been a surge of efforts adapting existing feature descriptors and designing new…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them…