Related papers: StairNet: Top-Down Semantic Aggregation for Accura…

Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches…

Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…

Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual…

As drone-based object detection technology continues to evolve, the demand is shifting from merely detecting objects to enabling users to accurately identify specific targets. For example, users can input particular targets as prompts to…

Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detectors struggle with effective features extraction for…

One-shot image semantic segmentation poses a challenging task of recognizing the object regions from unseen categories with only one annotated example as supervision. In this paper, we propose a simple yet effective Similarity Guidance…

CNN-based object detection methods have achieved significant progress in recent years. The classic structures of CNNs produce pyramid-like feature maps due to the pooling or other re-scale operations. The feature maps in different levels of…

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly…

Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune from ImageNet pre-trained models designed for image…

Video instance segmentation (VIS) is a new and critical task in computer vision. To date, top-performing VIS methods extend the two-stage Mask R-CNN by adding a tracking branch, leaving plenty of room for improvement. In contrast, we…

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection…

This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the major LiDAR perception tasks such as 3D semantic segmentation,…

This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categories: top-down and bottom-up methods. Top-down methods rely…

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of…

We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as…

The real-time detection of small objects in complex scenes, such as the unmanned aerial vehicle (UAV) photography captured by drones, has dual challenges of detecting small targets (<32 pixels) and maintaining real-time efficiency on…

Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects). The previous works…

In the manufacturing industry, defect detection is an essential but challenging task aiming to detect defects generated in the process of production. Though traditional YOLO models presents a good performance in defect detection, they still…

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable…

We'd like to share a simple tweak of Single Shot Multibox Detector (SSD) family of detectors, which is effective in reducing model size while maintaining the same quality. We share box predictors across all scales, and replace convolution…