# Rapid Salient Object Detection with Difference Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2507.01182 · HTML: https://mlsanity.com/paper/2507.01182/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 125 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [A Simple Pooling-Based Design for Real-Time Salient Object Detection](https://mlsanity.com/paper/1904.09569/) (2019)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)

## Built on by (most cited first, 10 of 10)

- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [PhysNeXt: Next-Generation Dual-Branch Structured Attention Fusion Network for Remote Photoplethysmography Measurement](https://mlsanity.com/paper/2603.19752/) (2026)
- [Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy](https://mlsanity.com/paper/2605.00719/) (2026)
- [Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition](https://mlsanity.com/paper/2604.01903/) (2026)
- [MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs](https://mlsanity.com/paper/2511.13735/) (2025)
- [DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection](https://mlsanity.com/paper/2511.18865/) (2025)
- [STGBD-Net: Spatio-temporal Gradient Basis Decomposition Network for Infrared Small Target Detection](https://mlsanity.com/paper/2512.03470/) (2025)
- [M4-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection](https://mlsanity.com/paper/2605.11760/) (2026)
- [Learning Spatially Adaptive Structural Coordination for Underwater Salient Object Detection](https://mlsanity.com/paper/2605.15535/) (2026)
- [Spectral-Spatial Synergistic Guided Network for Hyperspectral Salient Object Detection](https://mlsanity.com/paper/2607.21032/) (2026)

## Abstract (arXiv)

This paper addresses the challenge of deploying salient object detection (SOD) on resource-constrained devices with real-time performance. While recent advances in deep neural networks have improved SOD, existing top-leading models are computationally expensive. We propose an efficient network design that combines traditional wisdom on SOD and the representation power of modern CNNs. Like biologically-inspired classical SOD methods relying on computing contrast cues to determine saliency of image regions, our model leverages Pixel Difference Convolutions (PDCs) to encode the feature contrasts. Differently, PDCs are incorporated in a CNN architecture so that the valuable contrast cues are extracted from rich feature maps. For efficiency, we introduce a difference convolution reparameterization (DCR) strategy that embeds PDCs into standard convolutions, eliminating computation and parameters at inference. Additionally, we introduce SpatioTemporal Difference Convolution (STDC) for video SOD, enhancing the standard 3D convolution with spatiotemporal contrast capture. Our models, SDNet for image SOD and STDNet for video SOD, achieve significant improvements in efficiency-accuracy trade-offs. On a Jetson Orin device, our models with < 1M parameters operate at 46 FPS and 150 FPS on streamed images and videos, surpassing the second-best lightweight models in our experiments by more than 2× and 3× in speed with superior accuracy. Code will be available at https://github.com/hellozhuo/stdnet.git.