Related papers: Self-Calibrating Active Binocular Vision via Activ…
Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally improve its performance under a…
Auto-encoder is a special kind of neural network based on reconstruction. De-noising auto-encoder (DAE) is an improved auto-encoder which is robust to the input by corrupting the original data first and then reconstructing the original…
This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction…
Adaptability is central to autonomy. Intuitively, for high-dimensional learning problems such as navigating based on vision, internal models with higher complexity allow to accurately encode the information available. However, most learning…
Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the…
Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for…
In recent years, the use of bio-sensing signals such as electroencephalogram (EEG), electrocardiogram (ECG), etc. have garnered interest towards applications in affective computing. The parallel trend of deep-learning has led to a huge leap…
We investigate the potential of autoencoders (AEs) for building a joint communication and sensing (JCAS) system that enables communication with one user while detecting multiple radar targets and estimating their positions. Foremost, we…
This research aims to explore the application of deep learning in autonomous driving computer vision technology and its impact on improving system performance. By using advanced technologies such as convolutional neural networks (CNN),…
Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…
Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…
Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…
Precision robotic manipulation tasks (insertion, screwing, precisely pick, precisely place) are required in many scenarios. Previous methods achieved good performance on such manipulation tasks. However, such methods typically require…
In humans, intrinsic motivation is an important mechanism for open-ended cognitive development; in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is $\textit{episodic memory}$…
We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall…
Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive…
Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Protein function is inherently linked to its localization within the cell, and fluorescent microscopy data is an indispensable resource for learning representations of proteins. Despite major developments in molecular representation…