相关论文: RAFT: Recurrent All-Pairs Field Transforms for Opt…

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these…

Parameter-efficient finetuning (PEFT) methods effectively adapt large language models (LLMs) to diverse downstream tasks, reducing storage and GPU memory demands. Despite these advantages, several applications pose new challenges to PEFT…

Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To…

Current linearizing encoding models that predict neural responses to sensory input typically neglect neuroscience-inspired constraints that could enhance model efficiency and interpretability. To address this, we propose a new method called…

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods…

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on…

Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…

Initializing optical flow field by either sparse descriptor matching or dense patch matches has been proved to be particularly useful for capturing large displacements. In this paper, we present a pyramidal gradient matching approach that…

Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. Recently, projected gradient…

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely…

Precise 6D pose estimation of rigid objects from RGB images is a critical but challenging task in robotics, augmented reality and human-computer interaction. To address this problem, we propose DeepRM, a novel recurrent network architecture…

In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such…

Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream information extraction from…

We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net…

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…

The computational burden of the iterative sampling process remains a major challenge in diffusion-based Low-Light Image Enhancement (LLIE). Current acceleration methods, whether training-based or training-free, often lead to significant…

The Radio frequency (RF) fingerprinting technique makes highly secure device authentication possible for future networks by exploiting hardware imperfections introduced during manufacturing. Although this technique has received considerable…