Related papers: Navigating Simply, Aligning Deeply: Winning Soluti…

Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a…

While the robustness of vision models is often measured, their dependence on specific architectural design choices is rarely dissected. We investigate why certain vision architectures are inherently more robust to additive Gaussian noise…

Recent research in artificial intelligence and machine learning has largely emphasized general-purpose learning and ever-larger training sets and more and more compute. In contrast, I propose a hybrid, knowledge-driven, reasoning-based…

Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural…

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial…

Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpropagation at human V1 by testing the same five learning rules against macaque…

Visual grounding is the task of localising image regions from natural language queries and is critical for reasoning capable Graphical User Interface agents. Many existing methods rely on massive, noisy synthetic datasets. This work…

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such…

Neural Architecture Search (NAS) has proven effective in discovering new Convolutional Neural Network (CNN) architectures, particularly for scenarios with well-defined accuracy optimization goals. However, previous approaches often involve…

Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be capable of optimizing…

Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between…

Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human…

Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant…

In motor neuroscience, artificial recurrent neural networks models often complement animal studies. However, most modeling efforts are limited to data-fitting, and the few that examine virtual embodied agents in a reinforcement learning…

The rapid advances in artificial intelligence (AI) have largely been driven by scaling deep neural networks (DNNs) - increasing model size, data, and computational resources. Yet performance is ultimately governed by network dynamics. The…

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where…

Thanks to the evolving network depth, convolutional neural networks (CNNs) have achieved remarkable success across various embedded scenarios, paving the way for ubiquitous embedded intelligence. Despite its promise, the evolving network…

Neural structure search (NAS), as the mainstream approach to automate deep neural architecture design, has achieved much success in recent years. However, the performance estimation component adhering to NAS is often prohibitively costly,…