相关论文: Attribute Diversity Determines the Systematicity G…

Visual Question Answering (VQA) models often perform poorly on out-of-distribution data and struggle on domain generalization. Due to the multi-modal nature of this task, multiple factors of variation are intertwined, making generalization…

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…

Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In…

Combining multiple perceptual inputs and performing combinatorial reasoning in complex scenarios is a sophisticated cognitive function in humans. With advancements in multi-modal large language models, recent benchmarks tend to evaluate…

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response. However, close examination of the VQA problem reveals an…

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily studied isolated and focus on confined and abstract problem…

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural…

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…

The increasing capture and analysis of large-scale longitudinal health data offer opportunities to improve healthcare and advance medical understanding. However, a critical gap exists between (a) -- the observation of patterns and…

Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, like zero-shot object recognition, they perform surprisingly…

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges…

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including data source (e.g.…

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic…

Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly must be better at assembling facts. We show that this…

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same…