RT-DETRv4 introduces a cost‑effective distillation framework that leverages Vision Foundation Models to improve lightweight real‑time object detectors. The method uses a Deep Semantic Injector to embed high‑level VFM representations into deep detector layers and a Gradient‑guided Adaptive Modulation strategy to adjust semantic transfer intensity based on gradient norms. These techniques yield consistent performance gains across DETR‑based models without adding inference overhead, achieving state‑of‑the‑art COCO AP scores at high FPS.
By Zijun Liao, Yian Zhao, Xin Shan, Yu Yan, Chang Liu, Lei Lu, Xiangyang Ji, Jie Chen
arXiv:2609.10018v1 Announce Type: new
Abstract: EdgeAI systems are increasingly employing computer vision applications to enable intelligent, on-device decision-making in real-time. However, these de...
By Sudaksh Kalra, Dolly Sapra
FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.
By Muhammad Rehan, Haider Ali, Muhammad Ali Munir, Moaz Amjad
arXiv:2608.22368v1 Announce Type: new
Abstract: While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the S...
By Huaiyuan Qin, Gabriel James Goenawan, Zihang Lin, Muli Yang, Hongyuan Zhu
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
By Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz
The paper surveys Continual Test-Time Adaptation (CTTA), a framework that adapts pretrained computer‑vision models to non‑stationary target distributions without source data or labeled targets, while avoiding catastrophic forgetting and error accumulation. It formally defines the CTTA problem, categorizes existing methods into optimization‑based, parameter‑efficient, and architecture‑based families, and reviews representative techniques and benchmarks across standard evaluation settings. The survey also outlines current limitations and proposes future research directions, such as adapting foundation models and black‑box systems.
By Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang, Shuaicheng Niu, Taki Hasan Rafi, Jihun Hamm, Marco Pedersoli, Jose Dolz, Yunhui Guo
arXiv:2604. 15622v3 Announce Type: replace-cross Abstract: Always-on contextual AI runs language-aligned vision foundation models (VFMs) on edge devices, where the on-device model is the dominant continuous compute cost under strict latency and power limits.
By Yiwei Zhao, Yi Zheng, Huapeng Su, Jieyu Lin, Stefano Ambrogio, Cijo Jose, Michael Ramamonjisoa, Patrick Labatut, Barbara De Salvo, Chiao Liu, Phillip B. Gibbons, Ziyun Li
The paper introduces Test-Time Logit Prompting (TLP), a lightweight framework that adapts vision-language models to missing-modality inputs without accessing source training data. TLP optimizes logit prompts using uncertainty-aware adjustments and modality-complete consistency regularization, thereby maintaining prediction confidence and semantic consistency. Experiments on various benchmarks show that TLP improves recognition performance by up to 8% while requiring only a few hundred tunable parameters and minimal test-time optimization steps.
By Taixi Chen, Nancy Guo
arXiv:2608.29395v1 Announce Type: new
Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data tha...
By Pedram MohajerAnsari, Amir Salarpour, Run Wang, Mert D. Pes\'e
arXiv:2311. 07461v3 Announce Type: replace Abstract: Autonomous systems (AS) often rely on Deep Neural Network (DNN) classifiers to operate in complex and dynamically changing environments.
By Abanoub Ghobrial, Kerstin Eder
arXiv:2607. 22872v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining.
By Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel Rahman
SAGE (Saliency‑Annealed Gated Encoder) is a Vision Transformer‑based backbone that explicitly leverages saliency, global context, and high‑frequency details through a saliency‑guided architecture, an annealing training paradigm, and a two‑stage loss transition. It achieves state‑of‑the‑art or competitive results on a wide range of dense prediction tasks, including COCO object detection and segmentation, ADE20K segmentation, TinyImageNet classification, and DIOR‑R oriented detection, all using the same backbone with task‑specific decoders. The framework is notable for being the first to deliver multi‑task SOTA performance on Huawei Ascend NPUs.
By Le Yang, Yucheng Huang, Junyu Chen, Qi Dang, Xin Kong, Haifeng Huo, Qiang Zhao