Related papers: A Neural Network Model of Spatial and Feature-Base…

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the…

In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention…

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…

Visual reasoning is a long-term goal of vision research. In the last decade, several works have attempted to apply deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of the…

We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual…

We present a lightweight network that infers grouping and boundaries, including curves, corners and junctions. It operates in a bottom-up fashion, analogous to classical methods for sub-pixel edge localization and edge-linking, but with a…

Visual question answering (VQA) usesimage processing algorithms to process the image and natural language processing methods to understand and answer the question. VQA is helpful to a visually impaired person, can be used for the security…

Attention networks show promise for both vision and language tasks, by emphasizing relationships between constituent elements through weighting functions. Such elements could be regions in an image output by a region proposal network, or…

Recent advances in general-purpose AI systems with attention-based transformers offer a potential window into how the neocortex and cerebellum, despite their relatively uniform circuit architectures, give rise to diverse functions and,…

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…

Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passively process entire scenes at once, resulting in excessive…

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained categorization on the Stanford Dogs data set. In this work…

Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear…

A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling…

Convolutional neural networks (CNNs) were inspired by early findings in the study of biological vision. They have since become successful tools in computer vision and state-of-the-art models of both neural activity and behavior on visual…

Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ in numerous ways from those that give rise to human…

Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse…

Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to contextual information mediated by extensive horizontal and…

Self-attention networks (SANs) have drawn increasing interest due to their high parallelization in computation and flexibility in modeling dependencies. SANs can be further enhanced with multi-head attention by allowing the model to attend…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…