Related papers: Generalized Focal Loss: Learning Qualified and Dis…

In object detection, multi-level prediction (e.g., FPN) and reweighting skills (e.g., focal loss) have drastically improved one-stage detector performance. However, the synergy between these two techniques is not fully explored in a unified…

Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required. In this paper,…

Zero-shot learning(ZSL) aims to recognize new classes without prior exposure to their samples, relying on semantic knowledge from observed classes. However, current attention-based models may overlook the transferability of visual features…

Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose…

Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry…

Monocular 3D object detection (Mono3D) has achieved tremendous improvements with emerging large-scale autonomous driving datasets and the rapid development of deep learning techniques. However, caused by severe domain gaps (e.g., the field…

Is it possible to detect arbitrary objects from a single example? A central problem of all existing attempts at one-shot object detection is the generalization gap: Object categories used during training are detected much more reliably than…

Image retrieval is the problem of searching an image database for items that are similar to a query image. To address this task, two main types of image representations have been studied: global and local image features. In this work, our…

Deep learning has been widely recognized as a promising approach in different computer vision applications. Specifically, one-stage object detector and two-stage object detector are regarded as the most important two groups of Convolutional…

In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization…

Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of…

LiDAR-based 3D object detection models often struggle to generalize to real-world environments due to limited object diversity in existing datasets. To tackle it, we introduce the first generalized cross-domain few-shot (GCFS) task in 3D…

Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental…

3D object detection based on point clouds has become more and more popular. Some methods propose localizing 3D objects directly from raw point clouds to avoid information loss. However, these methods come with complex structures and…

Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors…

Generalized Category Discovery (GCD) aims to identify unlabeled samples by leveraging the base knowledge from labeled ones, where the unlabeled set consists of both base and novel classes. Since clustering methods are time-consuming at…

Object localization in general environments is a fundamental part of vision systems. While dominating on the COCO benchmark, recent Transformer-based detection methods are not competitive in diverse domains. Moreover, these methods still…

Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…