Related papers: Pooling Pyramid Network for Object Detection
Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited…
We investigate the direction of training a 3D object detector for new object classes from only 2D bounding box labels of these new classes, while simultaneously transferring information from 3D bounding box labels of the existing classes.…
RGB-D salient object detection (SOD) has been in the spotlight recently because it is an important preprocessing operation for various vision tasks. However, despite advances in deep learning-based methods, RGB-D SOD is still challenging…
Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep…
In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were…
In modern computer vision tasks, convolutional neural networks (CNNs) are indispensable for image classification tasks due to their efficiency and effectiveness. Part of their superiority compared to other architectures, comes from the fact…
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…
Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian…
Small object detection for 3D point cloud is a challenging problem because of two limitations: (1) Perceiving small objects is much more diffcult than normal objects due to the lack of valid points. (2) Small objects are easily blocked…
Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…
Small object detection presents a significant challenge in computer vision and object detection. The performance of small object detectors is often compromised by a lack of pixels and less significant features. This issue stems from…
Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation…
Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally…
To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds. Our approach needs multi-frame point clouds only…
For object detection, it is possible to view the prediction of bounding boxes as a reverse diffusion process. Using a diffusion model, the random bounding boxes are iteratively refined in a denoising step, conditioned on the image. We…
Traditional deep learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to facilitate model propagation and fully connected…
Object proposal is essential for current state-of-the-art object detection pipelines. However, the existing proposal methods generally fail in producing results with satisfying localization accuracy. The case is even worse for small objects…
Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets. However, do we really…
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five…
Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We…