Related papers: Spatial Self-Distillation for Object Detection wit…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

Event cameras are gaining popularity due to their unique properties, such as their low latency and high dynamic range. One task where these benefits can be crucial is real-time object detection. However, RGB detectors still outperform…

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient…

Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating…

While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific…

Deep learning models have demonstrated remarkable success in object detection, yet their complexity and computational intensity pose a barrier to deploying them in real-world applications (e.g., self-driving perception). Knowledge…

Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation. While this approach alleviates the need for extensive point-level annotations, obtaining accurate bounding boxes in practical…

Self-distillation (SD) is the process of first training a \enquote{teacher} model and then using its predictions to train a \enquote{student} model with the \textit{same} architecture. Specifically, the student's objective function is…

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap between LiDAR-based and monocular-based methods. In this paper,…

Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their…

Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. A common approach used in WSOD to deal with the lack of localization information is Multiple Instance…

Exploiting pseudo labels (e.g., categories and bounding boxes) of unannotated objects produced by a teacher detector have underpinned much of recent progress in semi-supervised object detection (SSOD). However, due to the limited…

Weakly supervised object detection(WSOD) task uses only image-level annotations to train object detection task. WSOD does not require time-consuming instance-level annotations, so the study of this task has attracted more and more…

In this paper, we propose an efficient feature pruning strategy for 3D small object detection. Conventional 3D object detection methods struggle on small objects due to the weak geometric information from a small number of points. Although…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…