Related papers: DaD: Distilled Reinforcement Learning for Diverse …

Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to UDA-OD based on self-training have been effective in…

Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects. Existing methods typically estimate the object likelihood with an additional…

In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural language processing. To better leverage the potential of…

Few-shot learning for image classification comes up as a hot topic in computer vision, which aims at fast learning from a limited number of labeled images and generalize over the new tasks. In this paper, motivated by the idea of Fisher…

Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap…

Feature generation involves creating new features from raw data to capture complex relationships among the original features, improving model robustness and machine learning performance. Current methods using reinforcement learning for…

Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model…

Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic information,…

Reinforcement learning can solve decision-making problems and train an agent to behave in an environment according to a predesigned reward function. However, such an approach becomes very problematic if the reward is too sparse and so the…

Vision-centric perception systems for autonomous driving have gained considerable attention recently due to their cost-effectiveness and scalability, especially compared to LiDAR-based systems. However, these systems often struggle in…

Deep neural networks (DNNs) remain challenged by distribution shifts in complex open-world domains like automated driving (AD): Robustness against yet unknown novel objects (semantic shift) or styles like lighting conditions (covariate…

Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. To tackle the problem, previous works focus on aligning features extracted from…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Multimodal sensing reduces beam training overhead but is constrained by machine learning complexity and dataset demands. To address this, we propose a data-free (DF) knowledge distillation (KD) framework for efficient LiDAR-aided mmWave…

We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification…

Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with the help of adversarially trained models. Although existing…

In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and…

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning…

We present a novel framework to automatically learn to transform the differential cues from a stack of images densely captured with a rotational motion into spatially discriminative and view-invariant per-pixel features at each view. These…

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…