Related papers: Disentangle Your Dense Object Detector

Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and…

Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design…

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably…

This paper proposes a novel loss function for training a distributed convolutional neural network (DisCNN) to recognize only a specific positive class. By mapping positive samples to a compact set in high-dimensional space and negative…

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this…

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…

Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-style contrastive…

The uprising trend of deep learning in computer vision and artificial intelligence can simply not be ignored. On the most diverse tasks, from recognition and detection to segmentation, deep learning is able to obtain state-of-the-art…

Object detection is a famous branch of research in computer vision, many state of the art object detection algorithms have been introduced in the recent past, but how good are those object detectors when it comes to dense object detection?…

Recent weakly supervised video anomaly detection methods have achieved significant advances by employing unified frameworks for joint optimization. However, this paradigm is limited by a fundamental sensitivity-stability trade-off, as the…

Object detection is the identification of an object in the image along with its localisation and classification. It has wide spread applications and is a critical component for vision based software systems. This paper seeks to perform a…

Over the years various methods have been proposed for the problem of object detection. Recently, we have witnessed great strides in this domain owing to the emergence of powerful deep neural networks. However, there are typically two main…

Query-based object detectors directly decode image features into object instances with a set of learnable queries. These query vectors are progressively refined to stable meaningful representations through a sequence of decoder layers, and…

The precise localization of 3D objects from a single image without depth information is a highly challenging problem. Most existing methods adopt the same approach for all objects regardless of their diverse distributions, leading to…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…

Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to…

Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed all of which rely on the contour/edge information to improve…

Recently, anchor-free detection methods have been through great progress. The major two families, anchor-point detection and key-point detection, are at opposite edges of the speed-accuracy trade-off, with anchor-point detectors having the…

The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This effect is amplified in difficult tasks such as object detection. Dealing with errors in datasets is often…