Related papers: Object Detection Made Simpler by Eliminating Heuri…

Modern object detection networks pursuit higher precision on general object detection datasets, at the same time the computation burden is also increasing along with the improvement of precision. Nevertheless, the inference time and…

Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the costly ImageNet…

Recent object detectors find instances while categorizing candidate regions. As each region is evaluated independently, the number of candidate regions from a detector is usually larger than the number of objects. Since the final goal of…

In the object detection task, CNN (Convolutional neural networks) models always need a large amount of annotated examples in the training process. To reduce the dependency of expensive annotations, few-shot object detection has become an…

Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in…

Evaluating object detection models in deployment is challenging because ground-truth annotations are rarely available. We introduce the Cumulative Consensus Score (CCS), a label-free monitoring signal for continuous evaluation and…

CNN-based face detection methods have achieved significant progress in recent years. In addition to the strong representation ability of CNN, post-processing methods are also very important for the performance of face detection. In general,…

In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded quality of dense detection boxes…

Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the…

State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up segmentation-centric fashion wherein they build upon semantic segmentation networks by utilizing clustering to obtain object instances. In this paper, we re-think…

This paper demonstrates that Non-Maximum Suppression (NMS), which is commonly used in Object Detection (OD) tasks to filter redundant detection results, is no longer secure. Considering that NMS has been an integral part of OD systems,…

Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines. While essential object detection ingredients such as features, classifiers, and proposal methods have been extensively researched…

The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals by finding potential corner keypoint…

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,…

Presently, the task of few-shot object detection (FSOD) in remote sensing images (RSIs) has become a focal point of attention. Numerous few-shot detectors, particularly those based on two-stage detectors, face challenges when dealing with…

Few-shot semantic segmentation (FSS) aims to segment objects of novel categories in the query images given only a few annotated support samples. Existing methods primarily build the image-level correlation between the support target object…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

Object detection requires substantial labeling effort for learning robust models. Active learning can reduce this effort by intelligently selecting relevant examples to be annotated. However, selecting these examples properly without…

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…