Recursive Contour Saliency Blending Network for Accurate Salient Object Detection

• URL: http://arxiv.org/abs/2105.13865v2
• Date: Mon, 31 May 2021 02:43:47 GMT
• Title: Recursive Contour Saliency Blending Network for Accurate Salient Object Detection
• Authors: Yi Ke Yun, Chun Wei Tan, Takahiro Tsubono
• Abstract summary: In this work, we designed a network for better edge quality in salient object detection. We proposed a contour-saliency blending module to exchange information between contour and saliency. Our model is lightweight and fast, with only 27.9 million parameters and real-time inferencing at 31 FPS.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Contour information plays a vital role in salient object detection. However, excessive false positives remain in predictions from existing contour-based models due to insufficient contour-saliency fusion. In this work, we designed a network for better edge quality in salient object detection. We proposed a contour-saliency blending module to exchange information between contour and saliency. We adopted recursive CNN to increase contour-saliency fusion while keeping the total trainable parameters the same. Furthermore, we designed a stage-wise feature extraction module to help the model pick up the most helpful features from previous intermediate saliency predictions. Besides, we proposed two new loss functions, namely Dual Confinement Loss and Confidence Loss, for our model to generate better boundary predictions. Evaluation results on five common benchmark datasets reveal that our model achieves competitive state-of-the-art performance. Last but not least, our model is lightweight and fast, with only 27.9 million parameters and real-time inferencing at 31 FPS.

Related papers

• Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detection [8.531052087985097]
  Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. We propose Decoupled and Interactive Regression Modeling (DIRM) for one-stage detection.
  arXiv  Detail & Related papers  (2024-09-01T10:47:22Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Uncertainty modeling for fine-tuned implicit functions [10.902709236602536]
  Implicit functions have become pivotal in computer vision for reconstructing detailed object shapes from sparse views. We introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions. Our results show that Dropsembles achieve the accuracy and calibration levels of deep ensembles but with significantly less computational cost.
  arXiv  Detail & Related papers  (2024-06-17T20:46:18Z)
• Part-Based Models Improve Adversarial Robustness [57.699029966800644]
  We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks. Our model combines a part segmentation model with a tiny classifier and is trained end-to-end to simultaneously segment objects into parts. Our experiments indicate that these models also reduce texture bias and yield better robustness against common corruptions and spurious correlations.
  arXiv  Detail & Related papers  (2022-09-15T15:41:47Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation [50.08080424613603]
  Long-range correlation is essential for accurate monocular depth estimation. We propose to leverage the Transformer to model this global context with an effective attention mechanism. Our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins.
  arXiv  Detail & Related papers  (2022-03-27T05:03:56Z)
• Densely connected neural networks for nonlinear regression [8.830042935753303]
  We propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation (0.91) with observations.
  arXiv  Detail & Related papers  (2021-07-29T03:41:56Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)
• A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty [33.627068152037815]
  We present a novel symmetric matrix representation of the 3D rotation group, SO(3), with two important properties that make it particularly suitable for learned models. We empirically validate the benefits of our formulation by training deep neural rotation regressors on two data modalities. This capability is key for safety-critical applications where detecting novel inputs can prevent catastrophic failure of learned models.
  arXiv  Detail & Related papers  (2020-06-01T15:57:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.