Related papers: Robust Vision Challenge 2020 -- 1st Place Report f…

We propose a new residual block for convolutional neural networks and demonstrate its state-of-the-art performance in medical image segmentation. We combine attention mechanisms with group convolutions to create our group attention…

Object detection is a challenging task in visual understanding domain, and even more so if the supervision is to be weak. Recently, few efforts to handle the task without expensive human annotations is established by promising deep neural…

Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions without shared computation and task association. We aim to unify…

This paper presents our proposed methods to ICDAR 2021 Robust Reading Challenge - Integrated Circuit Text Spotting and Aesthetic Assessment (ICDAR RRC-ICTEXT 2021). For the text spotting task, we detect the characters on integrated circuit…

Existing open-world universal segmentation approaches usually leverage CLIP and pre-computed proposal masks to treat open-world segmentation tasks as proposal classification. However, 1) these works cannot handle universal segmentation in…

Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to its complex real-world challenges. To solve this problem, we…

In this paper, we present a comprehensive point cloud semantic segmentation network that aggregates both local and global multi-scale information. First, we propose an Angle Correlation Point Convolution (ACPConv) module to effectively…

Many two-stage instance segmentation heads predict a coarse 28x28 mask per instance, which is insufficient to capture the fine-grained details of many objects. To address this issue, PointRend and RefineMask predict a 112x112 segmentation…

We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn…

Scene understanding plays a critical role in enabling intelligence and autonomy in robotic systems. Traditional approaches often face challenges, including occlusions, ambiguous boundaries, and the inability to adapt attention based on…

In this work, we introduce panoramic panoptic segmentation, as the most holistic scene understanding, both in terms of Field of View (FoV) and image-level understanding for standard camera-based input. A complete surrounding understanding…

We consider an important task of effective and efficient semantic image segmentation. In particular, we adapt a powerful semantic segmentation architecture, called RefineNet, into the more compact one, suitable even for tasks requiring…

This report describes the systems submitted to the first and second tracks of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020, which ranked second in both tracks. Three key points of the system pipeline are explored: (1)…

3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature…

As intensities of MRI volumes are inconsistent across institutes, it is essential to extract universal features of multi-modal MRIs to precisely segment brain tumors. In this concept, we propose a volumetric vision transformer that follows…

Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in…

Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework. However, an efficient solution for…

Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large language models and vision language models based…

Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmentation (pixel level classification) and instance segmentation…

The performance of face detectors has been largely improved with the development of convolutional neural network. However, it remains challenging for face detectors to detect tiny, occluded or blurry faces. Besides, most face detectors…