We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...
Abstract: Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). However, compared to high-level ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results