Related papers: Rethinking Classification and Localization for Cas…
Detection and tracking of moving objects is an essential component in environmental perception for autonomous driving. In the flourishing field of multi-view 3D camera-based detectors, different transformer-based pipelines are designed to…
Complicated underwater environments bring new challenges to object detection, such as unbalanced light conditions, low contrast, occlusion, and mimicry of aquatic organisms. Under these circumstances, the objects captured by the underwater…
We present consistent optimization for single stage object detection. Previous works of single stage object detectors usually rely on the regular, dense sampled anchors to generate hypothesis for the optimization of the model. Through an…
We study the problem of weakly semi-supervised object detection with points (WSSOD-P), where the training data is combined by a small set of fully annotated images with bounding boxes and a large set of weakly-labeled images with only a…
Recently, anchor-free detection methods have been through great progress. The major two families, anchor-point detection and key-point detection, are at opposite edges of the speed-accuracy trade-off, with anchor-point detectors having the…
The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object…
Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such…
Overhead line inspection greatly benefits from defect recognition using visible light imagery. Addressing the limitations of existing feature extraction techniques and the heavy data dependency of deep learning approaches, this paper…
Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces, as well as the accuracy of object localization within the 3D space. This paper aims to address such a fundamental problem…
Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In…
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This…
Anchor-free object detectors are highly efficient in performing point-based prediction without the need for extra post-processing of anchors. However, different from the 2D grids, the 3D points used in these detectors are often far from the…
Feature pyramid network (FPN) has been an effective framework to extract multi-scale features in object detection. However, current FPN-based methods mostly suffer from the intrinsic flaw of channel reduction, which brings about the loss of…
As one of the prevalent components, Feature Pyramid Network (FPN) is widely used in current object detection models for improving multi-scale object detection performance. However, its feature fusion mode is still in a misaligned and local…
Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and…
The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to…
This study presents a divide-and-conquer (DC) approach based on feature space decomposition for classification. When large-scale datasets are present, typical approaches usually employed truncated kernel methods on the feature space or DC…
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…
Modern retrospective analytics systems leverage cascade architecture to mitigate bottleneck for computing deep neural networks (DNNs). However, the existing cascades suffer two limitations: (1) decoding bottleneck is either neglected or…
We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…