The crux of semi-supervised semantic segmentation is to assign pseudo-labels to the pixels
of unlabeled images. A common practice is to select the highly confident predictions as the …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

The emerging field of artificial intelligence of things (AIoT, AI+ IoT) is driven by the
widespread use of intelligent infrastructures and the impressive success of deep learning …

Abstract Current Knowledge Distillation (KD) methods for semantic segmentation often
guide the student to mimic the teacher's structured information generated from individual …

In the past decade, autonomous vehicle systems (AVS) have advanced at an exponential
rate, particularly due to improvements in artificial intelligence, which have had a significant …

Humans are able to recognize structured relations in observation, allowing us to decompose
complex scenes into simpler parts and abstract the visual world in multiple levels. However …

Learning semantic segmentation from weakly-labeled (eg, image tags only) data is
challenging since it is hard to infer dense object regions from sparse semantic tags. Despite …

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

Deriving reliable region-word alignment from image-text pairs is critical to learnobject-level
vision-language representations for open-vocabulary object detection. Existing methods …

Point cloud segmentation is fundamental in understanding 3D environments. However,
current 3D point cloud segmentation methods usually perform poorly on scene boundaries …