相关论文: Modularity Matters: Learning Invariant Relational …

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable…

The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…

Although deep networks have recently emerged as the model of choice for many computer vision problems, in order to yield good results they often require time-consuming architecture search. To combat the complexity of design choices, prior…

For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are…

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…

During the last years, there has been a lot of interest in achieving some kind of complex reasoning using deep neural networks. To do that, models like Memory Networks (MemNNs) have combined external memory storages and attention…

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly…

For a given stable recurrent neural network (RNN) that is trained to perform a classification task using sequential inputs, we quantify explicit robustness bounds as a function of trainable weight matrices. The sequential inputs can be…

We present a distributed algorithm that enables a group of robots to collaboratively optimize the parameters of a deep neural network model while communicating over a mesh network. Each robot only has access to its own data and maintains…

This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods…

The application of deep learning to symbolic domains remains an active research endeavour. Graph neural networks (GNN), consisting of trained neural modules which can be arranged in different topologies at run time, are sound alternatives…

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…

Deep generative models have been applied to multiple applications in image-to-image translation. Generative Adversarial Networks and Diffusion Models have presented impressive results, setting new state-of-the-art results on these tasks.…

Attention mechanisms have been boosting the performance of deep learning models on a wide range of applications, ranging from speech understanding to program induction. However, despite experiments from psychology which suggest that…

Image restoration (IR) is a long-standing task to recover a high-quality image from its corrupted observation. Recently, transformer-based algorithms and some attention-based convolutional neural networks (CNNs) have presented promising…

Emerging evidence shows that the modular organization of the human brain allows for better and efficient cognitive performance. Many of these cognitive functions are very fast and occur in subsecond time scale such as the visual object…

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…

Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent…

We present a model inspired by the Global Workspace Theory that integrates specialized modules to perform a sequential reasoning task. A controller selectively routes information between modules through the workspace using a gating…

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…