Progressive Self-Guided Loss for Salient Object Detection

Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff

Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable balance between efficiency and accuracy. To this end, we design a lightweight framework while maintaining satisfying competitive accuracy. Specifically, we propose a novel trilateral decoder framework by decoupling the U-shape structure into three complementary branches, which are devised to confront the dilution of semantic context, loss of spatial structure and absence of boundary detail, respectively. Along with the fusion of three branches, the coarse segmentation results are gradually refined in structure details and boundary quality. Without adding additional learnable parameters, we further propose Scale-Adaptive Pooling Module to obtain multi-scale receptive field. In particular, on the premise of inheriting this framework, we rethink the relationship among accuracy, parameters and speed via network depth-width tradeoff. With these insightful considerations, we comprehensively design shallower and narrower models to explore the maximum potential of lightweight SOD. Our models are proposed for different application environments: 1) a tiny version CTD-S (1.7M, 125FPS) for resource constrained devices, 2) a fast version CTD-M (12.6M, 158FPS) for speed-demanding scenarios, 3) a standard version CTD-L (26.5M, 84FPS) for high-performance platforms. Extensive experiments validate the superiority of our method, which achieves better efficiency-accuracy balance across five benchmarks.

Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment

With the popularity of mobile Internet, audio and video (A/V) have become the main way for people to entertain and socialize daily. However, in order to reduce the cost of media storage and transmission, A/V signals will be compressed by service providers before they are transmitted to end-users, which inevitably causes distortions in the A/V signals and degrades the end-user's Quality of Experience (QoE). This motivates us to research the objective audio-visual quality assessment (AVQA). In the field of AVQA, most previous works only focus on single-mode audio or visual signals, which ignores that the perceptual quality of users depends on both audio and video signals. Therefore, we propose an objective AVQA architecture for multi-mode signals based on attentional neural networks. Specifically, we first utilize an attention prediction model to extract the salient regions of video frames. Then, a pre-trained convolutional neural network is used to extract short-time features of the salient regions and the corresponding audio signals. Next, the short-time features are fed into Gated Recurrent Unit (GRU) networks to model the temporal relationship between adjacent frames. Finally, the fully connected layers are utilized to fuse the temporal related features of A/V signals modeled by the GRU network into the final quality score. The proposed architecture is flexible and can be applied to both full-reference and no-reference AVQA. Experimental results on the LIVE-SJTU Database and UnB-AVC Database demonstrate that our model outperforms the state-of-the-art AVQA methods. The code of the proposed method will be publicly available to promote the development of the field of AVQA.

Boosting Broader Receptive Fields for Salient Object Detection

Salient Object Detection has boomed in recent years and achieved impressive performance on regular-scale targets. However, existing methods encounter performance bottlenecks in processing objects with scale variation, especially extremely large- or small-scale objects with asymmetric segmentation requirements, since they are inefficient in obtaining more comprehensive receptive fields. With this issue in mind, this paper proposes a framework named BBRF for Boosting Broader Receptive Fields, which includes a Bilateral Extreme Stripping (BES) encoder, a Dynamic Complementary Attention Module (DCAM) and a Switch-Path Decoder (SPD) with a new boosting loss under the guidance of Loop Compensation Strategy (LCS). Specifically, we rethink the characteristics of the bilateral networks, and construct a BES encoder that separates semantics and details in an extreme way so as to get the broader receptive fields and obtain the ability to perceive extreme large- or small-scale objects. Then, the bilateral features generated by the proposed BES encoder can be dynamically filtered by the newly proposed DCAM. This module interactively provides spacial-wise and channel-wise dynamic attention weights for the semantic and detail branches of our BES encoder. Furthermore, we subsequently propose a Loop Compensation Strategy to boost the scale-specific features of multiple decision paths in SPD. These decision paths form a feature loop chain, which creates mutually compensating features under the supervision of boosting loss. Experiments on five benchmark datasets demonstrate that the proposed BBRF has a great advantage to cope with scale variation and can reduce the Mean Absolute Error over 20% compared with the state-of-the-art methods.

Improving RGB-D Salient Object Detection via Modality-Aware Decoder

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns - typically the combination of selective characteristics and its variations, are too highly dependent on the network's non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder's design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD.

Multiple refinement and integration network for Salient Object Detection

The purpose of the salient object detection (SOD) task is to suppress the background noise and segment the salient foreground regions. Some previous methods considered the strategies of background suppression and multi-level feature fusion. Other methods encountered the problem that single-scale convolution features are difficult to capture the correct object size. This paper reconsiders the above problems and proposes a comprehensive solution to achieve SOD for improving the detection performance and ensuring relatively fewer parameters. First, it is difficult to achieve a better refinement effect through only one refinement operation. To this end, a multi-scale denoising module (MSDM) and multi-pooling refinement module (MPRM) are proposed to jointly complete the refinement task of multi-level features. Besides, it is difficult to fully integrate complementary features through only one feature integration operation. Mutual learning module (MLM) is proposed to preliminarily integrate multi-level features. To reduce information redundancy, multi-attention (MA) mechanism is used to assist further integration. The proposed algorithm is called multiple refinement and integration network (MRINet). Experimental results on five benchmark datasets show that MRINet outperforms state-of-the-art methods on multiple evaluation metrics. Moreover, our ResNet-based algorithm only contains 25.202 million parameters, which is less than other ResNet-based algorithms and can run at over 37 fps on a single GPU. The code will be available at https://github.com/dc3234/MRINet.