Related papers: Hierarchical Cellular Automata for Visual Saliency
A number of psychological and physiological evidences suggest that early visual attention works in a coarse-to-fine way, which lays a basis for the reverse hierarchy theory (RHT). This theory states that attention propagates from the top…
Modern Vision--Language--Action models often suffer from critical instruction-following failures in high-density manipulation environments, where task-irrelevant visual clutter dilutes attention, corrupts grounding, and substantially…
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an…
Cellular Automata (CAs) are computational models that can capture the essential features of systems in which global behavior emerges from the collective effect of simple components, which interact locally. During the last decades, CAs have…
Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough,…
Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its…
A one-dimensional two-state number-conserving cellular automaton (NCCA) is a cellular automaton whose states are 0 or 1 and where cells take states 0 and 1 and updated their states by the rule which keeps overall sum of states constant. It…
Automatic Salient object detection has received tremendous attention from research community and has been an increasingly important tool in many computer vision tasks. This paper proposes a novel bottom-up salient object detection framework…
Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various…
Despite recent improvements in computer vision, artificial visual systems' design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the…
Our paper introduces a novel two-stage self-supervised approach for detecting co-occurring salient objects (CoSOD) in image groups without requiring segmentation annotations. Unlike existing unsupervised methods that rely solely on…
We say that a Cellular Automata (CA) is coalescing when its execution on two distinct (random) initial configurations in the same asynchronous mode (the same cells are updated in each configuration at each time step) makes both…
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which…
We study the predictability of emergent phenomena in complex systems. Using nearest neighbor, one-dimensional Cellular Automata (CA) as an example, we show how to construct local coarse-grained descriptions of CA in all classes of Wolfram's…
Training neural networks with discrete stochastic variables presents a unique challenge. Backpropagation is not directly applicable, nor are the reparameterization tricks used in networks with continuous stochastic variables. To address…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using…
Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complexity of Transformers. Recently, the emerging state-space…
We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks…
After an apparent hiatus of roughly 30 years, we revisit a seemingly neglected subject in the theory of (one-dimensional) cellular automata: sublinear-time computation. The model considered is that of ACAs, which are language acceptors…
This paper considers the estimation and inference of the low-rank components in high-dimensional matrix-variate factor models, where each dimension of the matrix-variates ($p \times q$) is comparable to or greater than the number of…