Highly Efficient Salient Object Detection with 100K Parameters
Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices. In this paper, we aim to relieve the contradiction between computation cost and model performance by improving the network efficiency to a higher degree. We propose a flexible convolutional module, namely generalized OctConv (gOctConv), to efficiently utilize both in-stage and cross-stages multi-scale features, while reducing the representation redundancy by a novel dynamic weight decay scheme. The effective dynamic weight decay scheme stably boosts the sparsity of parameters during training, supports learnable number of channels for each scale in gOctConv, allowing 80% of parameters reduce with negligible performance drop. Utilizing gOctConv, we build an extremely light-weighted model, namely CSNet, which achieves comparable performance with about 0.2% parameters (100k) of large models on popular salient object detection benchmarks.
Code (1)
Tasks
Objectobject-detectionObject DetectionRGB Salient Object DetectionSalient Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unconstrained Salient Object Detection via Proposal Subset Optimization
We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient objects (if any) varies from image to image, and is not given. We present a salient object detection system that…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1External Prompt Features Enhanced Parameter-efficient Fine-tuning for Salient Object Detection
Salient object detection (SOD) aims at finding the most salient objects in images and outputs pixel-level binary masks. Transformer-based methods achieve promising performance due to their global semantic understanding, …
Decoderobject-detectionObject Detectionparameter-efficient fine-tuning+1Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels
Computer vision algorithms with pixel-wise labeling tasks, such as semantic segmentation and salient object detection, have gone through a significant accuracy increase with the incorporation of deep learning. Deep segme…
Objectobject-detectionObject DetectionRGB Salient Object Detection+4Delving Into Salient Object Subitizing and Detection
Subitizing (i.e., instant judgement on the number) and detection of salient objects are human inborn abilities. These two tasks influence each other in the human visual system. In this paper, we delve into the complement…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1Cross-layer Feature Pyramid Network for Salient Object Detection
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. However, it is observed that these models o…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1