相关论文: Prime Sample Attention in Object Detection

Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention…

Sampling-based Model Predictive Control (MPC) is a flexible control framework that can reason about non-smooth dynamics and cost functions. Recently, significant work has focused on the use of machine learning to improve the performance of…

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…

Research on the distribution of prime numbers has revealed a dual character: deterministic in definition yet exhibiting statistical behavior reminiscent of random processes. In this paper we show that it is possible to use an image-focused…

Small object detection is a broadly investigated research task and is commonly conceptualized as a "pipeline-style" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where…

Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationships between sample…

In computational pathology, random sampling of patches during training of Multiple Instance Learning (MIL) methods is computationally efficient and serves as a regularization strategy. Despite its promising benefits, questions concerning…

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning…

Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However,…

In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the…

In recent years, deep learning based object detection methods have achieved promising performance in controlled environments. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges:…

Sample selection is a prevalent approach in learning with noisy labels, aiming to identify confident samples for training. Although existing sample selection methods have achieved decent results by reducing the noise rate of the selected…

Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves…

RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…

Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first…

Performance monitoring of object detection is crucial for safety-critical applications such as autonomous vehicles that operate under varying and complex environmental conditions. Currently, object detectors are evaluated using summary…

Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into…

Current state-of-the-art segmentation models encode entire images before focusing on specific objects. As a result, they waste computational resources - particularly when small objects are to be segmented in high-resolution scenes. We…

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing…

Teaching machines to recognize a new category based on few training samples especially only one remains challenging owing to the incomprehensive understanding of the novel category caused by the lack of data. However, human can learn new…