# Highly Efficient Salient Object Detection with 100K Parameters

arXiv: https://arxiv.org/abs/2003.05643 · HTML: https://mlsanity.com/paper/2003.05643/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 30 of 79)

- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.02688/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Uncertainty-aware Joint Salient Object and Camouflaged Object Detection](https://mlsanity.com/paper/2104.02628/) (2021)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [Boundary-Guided Camouflaged Object Detection](https://mlsanity.com/paper/2207.00794/) (2022)
- [Deep Gradient Learning for Efficient Camouflaged Object Detection](https://mlsanity.com/paper/2205.12853/) (2022)
- [VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning](https://mlsanity.com/paper/2311.15011/) (2023)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [Global2Local: Efficient Structure Search for Video Action Segmentation](https://mlsanity.com/paper/2101.00910/) (2021)
- [One-Shot Object Affordance Detection in the Wild](https://mlsanity.com/paper/2108.03658/) (2021)
- [Disentangled High Quality Salient Object Detection](https://mlsanity.com/paper/2108.03551/) (2021)
- [Group Collaborative Learning for Co-Salient Object Detection](https://mlsanity.com/paper/2104.01108/) (2021)
- [One-Shot Affordance Detection](https://mlsanity.com/paper/2106.14747/) (2021)
- [OTOV2: Automatic, Generic, User-Friendly](https://mlsanity.com/paper/2303.06862/) (2023)
- [Densely Nested Top-Down Flows for Salient Object Detection](https://mlsanity.com/paper/2102.09133/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Towards Deeper Understanding of Camouflaged Object Detection](https://mlsanity.com/paper/2205.11333/) (2022)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [Salient Object Detection in Optical Remote Sensing Images Driven by Transformer](https://mlsanity.com/paper/2309.08206/) (2023)
- [Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment](https://mlsanity.com/paper/2301.02778/) (2023)
- [Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation](https://mlsanity.com/paper/2201.08049/) (2022)
- [Learning to Detect Instance-level Salient Objects Using Complementary Image Labels](https://mlsanity.com/paper/2111.10137/) (2021)

## Abstract (arXiv)

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.