Object detection in aerial images: A large-scale benchmark and challenges
In he past decade, object detection has achieved significant progress in natural images but
not in aerial images, due to the massive variations in the scale and orientation of objects …
not in aerial images, due to the massive variations in the scale and orientation of objects …
Decoupling classifier for boosting few-shot object detection and instance segmentation
BB Gao, X Chen, Z Huang, C Nie… - Advances in …, 2022 - proceedings.neurips.cc
This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS),
which requires a model to quickly adapt to novel classes with a few labeled instances. The …
which requires a model to quickly adapt to novel classes with a few labeled instances. The …
Box-level active detection
Active learning selects informative samples for annotation within budget, which has proven
efficient recently on object detection. However, the widely used active detection benchmarks …
efficient recently on object detection. However, the widely used active detection benchmarks …
Siod: Single instance annotated per category per image for object detection
Object detection under imperfect data receives great attention recently. Weakly supervised
object detection (WSOD) suffers from severe localization issues due to the lack of instance …
object detection (WSOD) suffers from severe localization issues due to the lack of instance …
Semi-supervised and long-tailed object detection with cascadematch
This paper focuses on long-tailed object detection in the semi-supervised learning setting,
which poses realistic challenges, but has rarely been studied in the literature. We propose a …
which poses realistic challenges, but has rarely been studied in the literature. We propose a …
Co-mining: Self-supervised learning for sparsely annotated object detection
Object detectors usually achieve promising results with the supervision of complete instance
annotations. However, their performance is far from satisfactory with sparse instance …
annotations. However, their performance is far from satisfactory with sparse instance …
Ss3d: Sparsely-supervised 3d object detection from point cloud
Conventional deep learning based methods for 3D object detection require a large amount
of 3D bounding box annotations for training, which is expensive to obtain in practice …
of 3D bounding box annotations for training, which is expensive to obtain in practice …
Unsupervised object detection with lidar clues
Despite the importance of unsupervised object detection, to the best of our knowledge, there
is no previous work addressing this problem. One main issue, widely known to the …
is no previous work addressing this problem. One main issue, widely known to the …
Calibrated teacher for sparsely annotated object detection
Fully supervised object detection requires training images in which all instances are
annotated. This is actually impractical due to the high labor and time costs and the …
annotated. This is actually impractical due to the high labor and time costs and the …
Edge-compatible deep learning models for detection of pest outbreaks in viticulture
J Gonçalves, E Silva, P Faria, T Nogueira, A Ferreira… - Agronomy, 2022 - mdpi.com
The direct effect of global warming on viticulture is already apparent, with unexpected pests
and diseases as one of the most concerning consequences. Deploying sticky traps on grape …
and diseases as one of the most concerning consequences. Deploying sticky traps on grape …