arXiv Computer Vision August 27, 2026 By Zhaojian Yao, Wei Gao, Tiesong Zhao, Hui Yuan, Sam Kwong

MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection

Read the original on arXiv Computer Vision →

MIMONet is a saliency detection model that uses multi‑scale inputs and outputs to better handle objects of varying sizes. It processes three differently sized images through separate encoder branches that exchange information, allowing each branch to learn size‑variation knowledge from the others. A Multi‑scale Perception module further refines features, and a Joint Saliency Loss ensures consistent, well‑preserved boundaries across the multiple saliency maps produced.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

computer-vision

arXiv AI

Jul 10

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection

arXiv:2511. 12810v2 Announce Type: replace-cross Abstract: Camouflaged object detection is an emerging and challenging computer vision task that requires identifying and segmenting objects that blend seamlessly into their environments due to high similarity in color, texture, and size.

By Leena Alghamdi, Muhammad Usman, Hafeez Anwar, Abdul Bais, Saeed Anwar

llms computer-vision benchmarks

arXiv Machine Learning

Jun 30

CoLR-Det: Collaborative Latent Restoration for Small Object Detection in Low-Resolution Remote Sensing Images

arXiv:2601. 12507v2 Announce Type: replace-cross Abstract: Low-resolution remote sensing small object detection is limited by both missing visual details and the ambiguity of how details serve detection.

By Ruo Qi, Linhui Dai, Yusong Qin, Chaolei Yang, Yanshan Li

computer-vision benchmarks

arXiv AI

Jul 21

DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification

arXiv:2607. 16338v1 Announce Type: cross Abstract: This article presents DMFNet, a dual-backbone multiscale feature fusion framework with residual feature propagation and spatial attention for remote sensing scene classification.

By Anamitra Ghosh, Abhiroop Chatterjee, Susmita Ghosh

fine-tuning benchmarks

arXiv Computer Vision

2d ago

Context-Guided Semantic Alignment for Feature Fusion Networks

arXiv:2606.14005v2 Announce Type: replace Abstract: Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes....

By Hyungseop Lee, Jiho Lee, Woochul Kang

safety

arXiv AI

Aug 21

HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations

arXiv:2608. 19407v1 Announce Type: cross Abstract: Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs.

By Manasi Nerurkar, Ali A. Minai

safety

arXiv Computer Vision

4d ago

Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition

The paper introduces an Attention-Driven Complementarity Resampling framework to enhance cross-modality object detection. It employs a shared channel spatial attention mechanism that exchanges semantic masks between modalities, encouraging the backbone to learn generalized features. Additionally, a learnable channel competition module samples and aggregates features channel‑wise, improving robustness and achieving competitive results on multiple datasets.

By Guandi Wang, Ming Li, Yunsen Xing, Junle Liu

computer-vision multimodal benchmarks

One email a morning, machine-written

Related stories

MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection

CoLR-Det: Collaborative Latent Restoration for Small Object Detection in Low-Resolution Remote Sensing Images

DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification

Context-Guided Semantic Alignment for Feature Fusion Networks

HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations

Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition