Related papers: Distilling Knowledge from Refinement in Multiple I…
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We study the problem of learning localization model on target…
Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification, object detection, etc. However, few-shot object detection…
Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate…
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…
Real-time visual localization often utilizes online computing, for which query images or videos are transmitted to remote servers for visual place recognition (VPR). However, limited network bandwidth necessitates image-quality reduction…
Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This paper focuses on a more challenging but realistic class-incremental few-shot…
In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and…
Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and…
Detecting out-of-distribution (OOD) data is a task that is receiving an increasing amount of research attention in the domain of deep learning for computer vision. However, the performance of detection methods is generally evaluated on the…
Weed detection is a critical component of precision agriculture, facilitating targeted herbicide application and reducing environmental impact. However, deploying accurate object detection models on resource-limited platforms remains…
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…
Weakly supervised object detection~(WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques…
Drones are employed in a growing number of visual recognition applications. A recent development in cell tower inspection is drone-based asset surveillance, where the autonomous flight of a drone is guided by localizing objects of interest…
Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a…
The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…
The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping…
Previous video salient object detection (VSOD) approaches have mainly focused on designing fancy networks to achieve their performance improvements. However, with the slow-down in development of deep learning techniques recently, it may…
Classical object detectors are incapable of detecting novel class objects that are not encountered before. Regarding this issue, Open-Vocabulary Object Detection (OVOD) is proposed, which aims to detect the objects in the candidate class…
Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on…
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…