Related papers: Relational Proxies: Emergent Relationships as Fine…

Small, finite entities are easier and simpler to manipulate than gigantic, infinite ones. Consequently huge chunks of mathematics are devoted to methods reducing the study of big, cumbersome objects to an analysis of their finite building…

State-of-the-art object detectors are fast and accurate, but they require a large amount of well annotated training data to obtain good performance. However, obtaining a large amount of training annotations specific to a particular task,…

Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide changes in such environmental conditions, using training pairs of…

Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning-yet, large multimodal models (LMMs) struggle to perform this seemingly straightforward…

Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry frequently adopts is using off-the-shelf proxy models to…

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

This paper presents a conformal prediction method for classification in highly imbalanced and open-set settings, where there are many possible classes and not all may be represented in the data. Existing approaches require a finite, known…

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and books, and these objects typically relate to each other by…

Natural language inference has trended toward studying contexts beyond the sentence level. An important application area is law: past cases often do not foretell how they apply to new situations and implications must be inferred. This paper…

Current deep learning approaches have shown good in-distribution generalization performance, but struggle with out-of-distribution generalization. This is especially true in the case of tasks involving abstract relations like recognizing…

Fine-grained recognition in everyday life is often not a closed-book classification problem: when encountering unfamiliar objects, humans actively search, compare visual details, and verify evidence before deciding. Existing benchmarks…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences. Although learning different objects' local differences via Deep Neural Networks has achieved success, how…

Relational reasoning is the ability to infer relations that jointly bind multiple entities, attributes, or variables. This ability is central to scientific reasoning, but existing evaluations of relational reasoning in large language models…

Empirical researchers increasingly use upstream machine-learning (ML) methods to construct proxies for latent target variables from complex, unstructured data. A naive plug-in use of such proxies in downstream econometric models, however,…

Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning based pose regression methods have attracted many attentions. They feature predicting the absolute poses without relying on…

Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on…

Spatial relations between objects in an image have proved useful for structural object recognition. Structural constraints can act as regularization in neural network training, improving generalization capability with small datasets.…

Argument mining has garnered increasing attention over the years, with the recent advancement of Large Language Models (LLMs) further propelling this trend. However, current argument relations remain relatively simplistic and foundational,…

Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances. Particularly, industrial objects can have irregular shapes, that is, thin and concave, whereas in bin-picking…