Related papers: Mask-aware IoU for Anchor Assignment in Real-time …

In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one…

Are existing object detection methods adequate for detecting text and visual elements in scientific plots which are arguably different than the objects found in natural images? To answer this question, we train and compare the accuracy of…

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance…

In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features. Differentiating multiple potential instances within a single PoI feature is challenging because learning a high-dimensional…

Recently Deep Learning based Siamese Networks with region proposals for visual object tracking becoming more popular. These networks, while testing, perform extra computations on output if trained network, to predict the bounding box. This…

Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the…

We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst (conditional convolutions for instance and panoptic segmentation). In the literature, top-performing instance segmentation methods typically…

Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object…

3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection…

Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images. A subset of viewpoint-agnostic monocular 3D detection methods also do not explicitly leverage scene homography or geometry…

The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function - a measure of how accurately your ML model can predict the expected outcome. Conventional…

Marine debris poses a significant threat to the survival of marine wildlife, often leading to entanglement and starvation, ultimately resulting in death. Therefore, removing debris from the ocean is crucial to restore the natural balance…

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

Labeling pixel-wise object masks in videos is a resource-intensive and laborious process. Box-supervised Video Instance Segmentation (VIS) methods have emerged as a viable solution to mitigate the labor-intensive annotation process. . In…

Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous boundaries, overlapping instances, and weak inter-instance visual differences. While…

Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when…

Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of…

Multi-object tracking (MOT) in human-dominant scenarios, which involves continuously tracking multiple people within video sequences, remains a significant challenge in computer vision due to targets' complex motion and severe occlusions.…

Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without…

Accurate identification and localization of anatomical structures of varying size and appearance in laparoscopic imaging are necessary to leverage the potential of computer vision techniques for surgical decision support. Segmentation…