Related papers: From Open Set to Closed Set: Supervised Spatial Di…

Current perception models have achieved remarkable success by leveraging large-scale labeled datasets, but still face challenges in open-world environments with novel objects. To address this limitation, researchers introduce open-set…

Deep neural networks face several challenges in hyperspectral image classification, including complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features that often lead to missing…

Crowd counting is an important vision task, which faces challenges on continuous scale variation within a given scene and huge density shift both within and across images. These challenges are typically addressed using multi-column…

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of…

We have created a large diverse set of cars from overhead images, which are useful for training a deep learner to binary classify, detect and count them. The dataset and all related material will be made publically available. The set…

Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangled representations to discriminate in-distribution (ID) and OOD data, neglecting the rich…

Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes…

Class-agnostic counting (CAC) has numerous potential applications across various domains. The goal is to count objects of an arbitrary category during testing, based on only a few annotated exemplars. In this paper, we point out that the…

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…

Object detection in high-resolution aerial images is a challenging task because of 1) the large variation in object size, and 2) non-uniform distribution of objects. A common solution is to divide the large aerial image into small (uniform)…

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The…

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly…

Open-set panoptic segmentation (OPS) problem is a new research direction aiming to perform segmentation for both \known classes and \unknown classes, i.e., the objects ("things") that are never annotated in the training set. The main…

Conventional open-world object detection (OWOD) problem setting first distinguishes known and unknown classes and then later incrementally learns the unknown objects when introduced with labels in the subsequent tasks. However, the current…

Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density…

Medical image datasets in the real world are often unlabeled and imbalanced, and Semi-Supervised Object Detection (SSOD) can utilize unlabeled data to improve an object detector. However, existing approaches predominantly assumed that the…

A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new…

The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-column CNN…

Recent remote sensing tech advancements drive imagery growth, making oriented object detection rapid development, yet hindered by labor-intensive annotation for high-density scenes. Oriented object detection with point supervision offers a…