Advanced Neural Network Applications

Latest papers

• LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder

  Anh-Khoa Dinh-Duc, Duc-Tai Dinh, Tam V. Nguyen, Minh-Triet Tran · 5 October 2026

  CLIP's visual encoder produces only global image representations, limiting its use in region-level tasks. Existing adaptations rely on visual prompting, input masking, or encoder fine-tuning, each compromising pre-trained representations. We propose LAS-CLIP, a Lightweight Adapter Steering approach …

• EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation

  Pujun Guo, Yuanfan Zheng, Fei Teng, Mengfei Duan, Guoqiang Zhao, Yuheng Zhang, Kai Luo, Kailun Yang · 5 October 2026

  Panoramic images provide a complete 360-degree field of view, enabling comprehensive scene understanding for embodied perception. However, heterogeneous embodied platforms exhibit substantial differences in observation viewpoints and spatial layouts, giving rise to cross-embodiment observation shift…

• ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling

  Hailun Xu, Kanchan Sarkar · 5 October 2026

  We study how to consolidate the current VITOK progress into a single multi-teacher distillation recipe that jointly preserves global recognition and dense semantics. Our starting point is an AM-RADIO-style student distilled from SigLIP2 and DINOv3-L, where SigLIP2 supplies strong global semantics an…

• FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters

  Wenya Su, Kai Luo, Di Wen, Ruiping Liu, Yufan Chen, Junwei Zheng, Kunyu Peng, Kailun Yang · 5 October 2026

  Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full f…

• Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces

  Yuxing Wang, Yizhou Wang, Anqi Li, Shuo Wang, Sameer Satish Pusegaonkar, Haoquan Liang, Jiajun Li, Shenxin Jiang, Jianhe Yuan, Shangru Li, Tongwei Dai, Zihao Chen, David C. Anastasiu, Sujit Biswas, Xunlei Wu, Zheng Tang · 5 October 2026

  Physical AI Smart Spaces is, to the best of our knowledge, the first benchmark to simultaneously provide large-scale, multi-class, and multi-camera 3D perception data for indoor smart spaces. It contains over 280 hours of synchronized 1080p footage captured by nearly 1,800 cameras in warehouses, hos…

• Spatial Lifting for Dense Prediction

  Mingzhi Xu, Tao Zhou, Yong Li, Yizhe Zhang · 2 October 2026

  We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a higher-dimensional space and subsequently processing them using networks designed for that higher dimension, such as a 3D U-Net. Counterintuitively, this…

• MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation

  Ivan Martinovi\'c, Josip \v{S}ari\'c, Yuki M. Asano, Sini\v{s}a \v{S}egvi\'c · 1 October 2026

  Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g., synthetic) and an unlabeled target domain to bridge the distribution gap. Existing panoptic UDA methods rely on teacher-student consistency learni…

• DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion

  ZiAn Wang, MingZhe Liu, Chaoyi Guo, ChangChun Li, Fangming Gu · 1 October 2026

  Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweigh…

• COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target Data

  Junjing Zheng, Zhiyi Zhou, Ningrui Yang, Hongying Meng · 1 October 2026

  Remote sensing object counting estimates how many buildings, vehicles, or ships appear in overhead images. Most supervised counters predict a density map, whose sum gives the object count, and assume similar categories, sizes, and backgrounds. Applying them across regions, sensors, or categories oft…

• On the Relaxation of Conditional Independence Assumption for Image Segmentation

  Zixun Wang, Ben Dai · 1 October 2026

  In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Ass…

• SANTA++: Sampling Attention through Representative Keys

  Kyle Lee, Christian Z. Pratt, Ruoyu Fang, Heekyung Lee, Avinash Lohitsa, Ryan Modafe, Kerem Y. Camsari · 30 September 2026

  Attention often concentrates on a small subset of tokens in the context, but which subset matters changes from one query to the next. To exploit this changing structure, we introduce SANTA++, a training-free stochastic attention method that uses representative keys for memory-efficient selection wit…

• When Can Attention Heads Be Statically Defined?

  Weixian Waylon Li, Yintao Tai, Marcio Fonseca, Shay B. Cohen · 30 September 2026

  Some attention heads learn similar patterns across inputs. Reusing these patterns could reduce training cost by avoiding repeated query-key score computation and softmax. Through controlled pretraining comparisons, we identify Selective Attention Freezing (SAF), which selects heads with low attentio…

• From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection

  Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener, Sidi Ahmed Mahmoudi, Matei Mancas · 30 September 2026

  Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety monitoring, data collection is costly, hazardous, and ethically constrained. This paper presents a systematic study comparing two complementary data gen…

• Embedded Bi-Temporal Building Damage Assessment for On-Board Data Reduction

  Thomas Goudemant, Benjamin Francesconi, Marjorie Bellizzi, Adrien Dorise · 30 September 2026

  Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire relevant imagery shortly after an event, but exploitation is limited by uplink and downlink capacity and by ground-processing latency. We address this with…

• Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs

  Shanfeng Huang, Zhou Fang, Song Xiao, Hai Du · 29 September 2026

  Regional-to-global distillation uses crop-conditioned guidance to improve full-image understanding. The challenge is to effectively transfer the teacher's crop-based advantage to the student's full-image inference. We propose progressive-view on-policy distillation (PVD), which shifts the student's …

• CASS: Contribution-Aware Structured Sparsity for Model Merging

  Yan Li, Guiping Cao, Meng Xu, Tao Jiang, Yaguang Song, Ming Tao, Yaowei Wang, Dongmei Jiang · 29 September 2026

  Model merging integrates task-specific fine-tuned models into a single multi-task model, but often suffers from parameter interference caused by conflicting task-vector updates. Existing methods typically mitigate conflicts by pruning task vectors based on weight magnitude or random heuristics, trea…

• AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation

  Soumyaratna Debnath, Weiming Zhang, Shriram Damodaran, Dingwen Xiao, Addison Lin Wang · 28 September 2026

  Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and alleviating projection-induced distortions. However, existing architectures often assume canonical spherical structure and stable viewpoints, which …

• CSCWD: Cross-Scale Channel-wise Knowledge Distillation for Lightweight Tiny Object Detection on Edge Devices

  Amir Zamani, Zeinab Ghasemi-Naraghi · 28 September 2026

  Real-time tiny object detection in aerial imagery is constrained by the weak spatial evidence of very small objects and the loss of high-resolution detail in lightweight detectors. This study presents Cross-Scale Channel-wise Knowledge Distillation (CSCWD), a training-time framework that transfers h…

• FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detection

  Ben Liang, Chao Sui, Junqi Bai, Yuan Liu, Chunlai Li, Xiubao Sui, Qian Chen · 25 September 2026

  In aerial RGB--IR object detection, effectively exploiting complementary information across modalities is critical for robust perception under complex illumination and environmental conditions. Existing multimodal detectors mainly focus on spatial-domain interaction or frequency-specific feature enh…

• RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation

  Shaohua Dong, Zexuan Meng, Haiyan Sun, Bing Fan, Cuicui Zhang, Dylan Joseph, Kewei Sha, Yunhe Feng, Heng Fan · 25 September 2026

  In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations. RGBD20K possesses several attractive properties: (1) Expanded Semantic Space. In particular, it…

• OD3: Optimization-free Dataset Distillation for Object Detection

  Salwa K. Al Khatib, Ahmed ElHagry, Shitong Shao, Zhiqiang Shen · 24 September 2026

  Training large neural networks on large-scale datasets requires substantial computational resources, particularly for dense prediction tasks such as object detection. Although dataset distillation (DD) has been proposed to alleviate these demands by synthesizing compact datasets from larger ones, mo…

• SMDDFNet: State-space Modeling and Dynamic Dual Fusion Network for Traffic Sign Detection

  TianYi Yu, DaJian Zhong, Lilin Wang · 24 September 2026

  Traffic sign detection is a challenging visual signal processing task for advanced driver assistance, where small objects, scale variation, and occlusion limit conventional detectors with fixed receptive fields. This paper proposes State-space Modeling and Dynamic Dual Fusion Network (SMDDFNet), a d…

• LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder

  Andrei Arhire, Mihaela-Elena Breab\u{a}n, Radu Timofte · 24 September 2026

  We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise decoder. LightMIS aligns the outputs of a five-level encoder to a common resolution using Scale-Aligned Projection blocks, aggregates them once, an…

• PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception

  Armin Maleki, Hayder Radha · 24 September 2026

  Heterogeneity across Collaborative Perception (CP) agents is a major challenge for emerging CP frameworks due to domain gaps from differing sensors, architectures, and training data. Prior works mitigate this challenge by aligning features in a unified space via model retraining or per-agent-type in…

• GTR: Gated Token Recurrence for Efficient Dense Prediction

  Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangjiang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen · 23 September 2026

  Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Recurrence (GTR), a softmax-free recurrent vision backbone that combines gated line…