Related papers: D3: Data Diversity Design for Systematic Generaliz…

Ensembles are widely used in machine learning and, usually, provide state-of-the-art performance in many prediction tasks. From the very beginning, the diversity of an ensemble has been identified as a key factor for the superior…

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

Visual recognition systems are meant to work in the real world. For this to happen, they must work robustly in any visual domain, and not only on the data used during training. Within this context, a very realistic scenario deals with…

The ability to compose learned concepts and apply them in novel settings is key to human intelligence, but remains a persistent limitation in state-of-the-art machine learning models. To address this issue, we introduce COGITAO, a modular…

Visual question answering (VQA) is the multi-modal task of answering natural language questions about an input image. Through cross-dataset adaptation methods, it is possible to transfer knowledge from a source dataset with larger train…

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…

One of the major challenges for evaluating the effectiveness of data visualizations and visual analytics tools arises from the fact that different users may be using these tools for different tasks. In this paper, we present a simple…

The quest for algorithms that enable cognitive abilities is an important part of machine learning. A common trait in many recently investigated cognitive-like tasks is that they take into account different data modalities, such as visual…

In this work, we propose a deep neural architecture that uses an attention mechanism which utilizes region based image features, the natural language question asked, and semantic knowledge extracted from the regions of an image to produce…

Visual object recognition systems need to generalize from a set of 2D training views to novel views. The question of how the human visual system can generalize to novel views has been studied and modeled in psychology, computer vision, and…

The Visual Question Answering (VQA) task combines challenges for processing data with both Visual and Linguistic processing, to answer basic `common sense' questions about given images. Given an image and a question in natural language, the…

Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or inhibit it are fully understood. In this work, we conduct a…

Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice. When instead learning layouts and modules jointly, compositionality does not…

Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different…

Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by…

Deep learning has been extensively used in various fields, such as phase imaging, 3D imaging reconstruction, phase unwrapping, and laser speckle reduction, particularly for complex problems that lack analytic models. Its data-driven nature…

Despite their importance in training artificial intelligence systems, large datasets remain challenging to acquire. For example, the ImageNet dataset required fourteen million labels of basic human knowledge, such as whether an image…

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to…

Visual Question Answering(VQA) is a highly complex problem set, relying on many sub-problems to produce reasonable answers. In this paper, we present the hypothesis that Visual Question Answering should be viewed as a multi-task problem,…

Learned systems in the domain of visual recognition and cognition impress in part because even though they are trained with datasets many orders of magnitude smaller than the full population of possible images, they exhibit sufficient…