Visual recognition with deep nearest centroids
We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …
Clustseg: Clustering for universal segmentation
We present CLUSTSEG, a general, transformer-based framework that tackles different
image segmentation tasks (ie, superpixel, semantic, instance, and panoptic) through a …
image segmentation tasks (ie, superpixel, semantic, instance, and panoptic) through a …
Label-efficient video object segmentation with motion clues
Video object segmentation (VOS) plays an important role in video analysis and
understanding, which in turn facilitates a number of diverse applications, including video …
understanding, which in turn facilitates a number of diverse applications, including video …
Boosting knowledge distillation via intra-class logit distribution smoothing
C Li, G Cheng, J Han - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Previous arts built an intimate link between knowledge distillation (KD) and label smoothing
(LS) that they both impose regularization on the model training. In this paper, we delve …
(LS) that they both impose regularization on the model training. In this paper, we delve …
LWSE: a lightweight stacked ensemble model for accurate detection of multiple chest infectious diseases including COVID-19
Recently, the COVID-19 disease has significantly impacted global economies and
healthcare systems. Swift and accurate detection of COVID-19 is crucial for effectively …
healthcare systems. Swift and accurate detection of COVID-19 is crucial for effectively …
Mitigating the curse of dimensionality for certified robustness via dual randomized smoothing
Randomized Smoothing (RS) has been proven a promising method for endowing an
arbitrary image classifier with certified robustness. However, the substantial uncertainty …
arbitrary image classifier with certified robustness. However, the substantial uncertainty …
Deep Multibranch Fusion Residual Network and IoT-based pest detection system using sound analytics in large agricultural field
RK Dhanaraj, MA Ali, AK Sharma, A Nayyar - Multimedia Tools and …, 2024 - Springer
In the modern era, agriculture is necessary for human existence globally, and it is imperative
to work toward increasing agricultural yields. Yet, crop production may be affected due to the …
to work toward increasing agricultural yields. Yet, crop production may be affected due to the …
Adversarial examples in the physical world: A survey
Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial
examples, raising broad security concerns about their applications. Besides the attacks in …
examples, raising broad security concerns about their applications. Besides the attacks in …
{π-Jack}:{Physical-World} Adversarial Attack on Monocular Depth Estimation with Perspective Hijacking
Monocular depth estimation (MDE) plays a crucial role in modern autonomous driving (AD)
by facilitating 3-D scene understanding and interaction. While vulnerabilities in deep neural …
by facilitating 3-D scene understanding and interaction. While vulnerabilities in deep neural …
LapUNet: a novel approach to monocular depth estimation using dynamic laplacian residual U-shape networks
Y Xi, S Li, Z Xu, F Zhou, J Tian - Scientific Reports, 2024 - nature.com
Monocular depth estimation is an important but challenging task. Although the performance
has been improved by adopting various encoder-decoder architectures, the estimated depth …
has been improved by adopting various encoder-decoder architectures, the estimated depth …