Related papers: Cost-Efficient Multi-Scale Fovea for Semantic-Base…

In goal-directed visual tasks, human perception is guided by both top-down and bottom-up cues. At the same time, foveal vision plays a crucial role in directing attention efficiently. Modern research on bio-inspired computational attention…

The aim of this work is to establish how accurately a recent semantic-based foveal active perception model is able to complete visual tasks that are regularly performed by humans, namely, scene exploration and visual search. This model…

By and large, existing computational models of visual attention tacitly assume perfect vision and full access to the stimulus and thereby deviate from foveated biological vision. Moreover, modeling top-down attention is generally reduced to…

The human visual system processes images with varied degrees of resolution, with the fovea, a small portion of the retina, capturing the highest acuity region, which gradually declines toward the field of view's periphery. However, the…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention…

We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally…

Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors the size of image pixels and produce the best results when trained on…

While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…

Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving. To maintain real-time performance, many practical systems downsample the video stream. But this can hurt downstream…

Semantic segmentation is a vital problem in computer vision. Recently, a common solution to semantic segmentation is the end-to-end convolution neural network, which is much more accurate than traditional methods.Recently, the decoders…

In this paper, we address the semantic segmentation task with a deep network that combines contextual features and spatial information. The proposed Cross Attention Network is composed of two branches and a Feature Cross Attention (FCA)…

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…

Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…

Convolutional neural networks (CNNs) have proven effective for image processing tasks, such as object recognition and classification. Recently, CNNs have been enhanced with concepts of attention, similar to those found in biology. Much of…

We present a foveated object detector (FOD) as a biologically-inspired alternative to the sliding window (SW) approach which is the dominant method of search in computer vision object detection. Similar to the human visual system, the FOD…

Human visual attention on three-dimensional objects emerges from the interplay between bottom-up geometric processing and top-down semantic recognition. Existing 3D saliency methods rely on hand-crafted geometric features or learning-based…

Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing assistive systems in detecting fine-grained hazardous objects such as chairs, tables, and…

As the development of Large Language Models (LLMs) shifts from parameter scaling to inference-time collaboration, the Mixture-of-Agents (MoA) framework has emerged as a general paradigm to harness collective intelligence by layering diverse…

Visual attention mechanisms are a key component of neural network models for computer vision. By focusing on a discrete set of objects or image regions, these mechanisms identify the most relevant features and use them to build more…