ABSTRACT
We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a 300 ×400 image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/.
ABSTRACT
The U-shape structure has shown its advantage in salient object detection for efficiently combining multi-scale features. However, most existing U-shape-based methods focused on improving the bottom-up and top-down pathways while ignoring the connections between them. This paper shows that we can achieve the cross-scale information interaction by centralizing these connections, hence obtaining semantically stronger and positionally more precise features. To inspire the newly proposed strategy's potential, we further design a relative global calibration module that can simultaneously process multi-scale inputs without spatial interpolation. Our approach can aggregate features more effectively while introducing only a few additional parameters. Our approach can cooperate with various existing U-shape-based salient object detection methods by substituting the connections between the bottom-up and top-down pathways. Experimental results demonstrate that our proposed approach performs favorably against the previous state-of-the-arts on five widely used benchmarks with less computational complexity. The source code will be publicly available.
ABSTRACT
Salient object segmentation, edge detection, and skeleton extraction are three contrasting low-level pixel-wise vision problems, where existing works mostly focused on designing tailored methods for each individual task. However, it is inconvenient and inefficient to store a pre-trained model for each task and perform multiple different tasks in sequence. There are methods that solve specific related tasks jointly but require datasets with different types of annotations supported at the same time. In this paper, we first show some similarities shared by these tasks and then demonstrate how they can be leveraged for developing a unified framework that can be trained end-to-end. In particular, we introduce a selective integration module that allows each task to dynamically choose features at different levels from the shared backbone based on its own characteristics. Furthermore, we design a task-adaptive attention module, aiming at intelligently allocating information for different tasks according to the image content priors. To evaluate the performance of our proposed network on these tasks, we conduct exhaustive experiments on multiple representative datasets. We will show that though these tasks are naturally quite different, our network can work well on all of them and even perform better than current single-purpose state-of-the-art methods. In addition, we also conduct adequate ablation analyses that provide a full understanding of the design principles of the proposed framework. To facilitate future research, source code will be released.
ABSTRACT
In this study, a pyridine-degrading bacterium, Paracoccus denitrifican W12, was isolated. It was cultivated to grow on the surface of activated bamboo charcoal (ABC) particles so that the ABC turned into biological activated bamboo charcoal (BABC) covered with biofilm of the W12. Free cells of the W12 and the BABC were separately tested in removing pyridine from aqueous solution. The results showed that 0.31 g x L(-1) suspended growing-W12 completely degraded 48.70-1399 mg x L(-1) of pyridine within 26.5-48.9 h, while the BABC (attached growing-W12) degraded pyridine much more efficiently due to the combination of biodegradation and adsorption. When the dosage of BABC was 10.0 g x L(-1) at the temperature of 35 degrees C, 692.2 mg x L(-1) of pyridine was decreased by 52% in the first 3.6 h mainly by adsorption, then was totally removed within 23.7 h mainly by biodegradation. Increasing the dosage of BABC or batch of treatment promoted the efficiency of pyridine removal remarkably. The synergistic mechanism of BABC removing pyridine from aqueous solution was further discussed on the basis of its microstructure.
