检索结果-内蒙古大学图书馆

Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Haoran Wang, Ping Zhou, Zihan Zhang, Xu Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China APUS AI Lab China

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a pool of learnable prompts. Although effective, these methods introduce substantial computational overhead, primarily due to prompt pool querying and increased input sequence lengths from prompt concatenation. In this work, we present a novel prompt-based approach that addresses this limitation. Our method trains a single set of shared prompts across all tasks and, rather than concatenating prompts to the input, directly modifies the CLS token’s attention computation by adding the prompts to it. This simple and lightweight design not only significantly reduces computational complexity—both in terms of inference costs and the number of trainable parameters—but also eliminates the need to optimize prompt lengths for different downstream tasks, offering a more efficient yet powerful solution for rehearsal-free class-incremental learning. Extensive experiments across a diverse range of CIL benchmarks demonstrate the effectiveness of our approach, highlighting its potential to establish a new prompt-based CIL paradigm. Furthermore, experiments on general recognition benchmarks beyond the CIL setting also show strong performance, positioning our method as a promising candidate for a general parameter-efficient fine-tuning approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

学校读者我要写书评

暂无评论

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detecti...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenxin Li Shiyi Lan Jose M. Alvarez Zuxuan Wu Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing NVIDIA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their out-standing abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a “modernized” dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set.

关键词： Location awareness Three-dimensional displays Estimation Object detection Detectors Benchmark testing Transformers

Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding

学校读者我要写书评

暂无评论

Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vis...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wujian Peng Sicheng Xie Zuyao You Shiyi Lan Zuxuan Wu Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing NVIDIA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Vision language models (VLM) have demonstrated re-markable performance across various downstream tasks. However, understanding fine-grained visual-linguistic con-cepts, such as attributes and inter-object relationships, re-mains a significant challenge. While several benchmarks aim to evaluate VLMs in finer granularity, their primary fo-cus remains on the linguistic aspect, neglecting the visual dimension. Here, we highlight the importance of evaluating VLMs from both a textual and visual perspective. We intro-duce a progressive pipeline to synthesize images that vary in a specific attribute while ensuring consistency in all other aspects. Utilizing this data engine, we carefully design a benchmark, SPEC, to diagnose the comprehension of object size, position, existence, and count. Subsequently, we con-duct a thorough evaluation offour leading VLMs on SPEC. Surprisingly, their performance is close to random guess, revealing significant limitations. With this in mind, we pro-pose a simple yet effective approach to optimize VLMs in fine- grained understanding, achieving significant improve-ments on SPEC without compromising the zero-shot performance. Results on two additional fine-grained benchmarks also show consistent improvements, further validating the transferability of our approach. Code and data are available at https://***/wjpoom/SPEC.

关键词： visualization Computer vision Codes Computational modeling Pipelines Benchmark testing Linguistics

Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Conde, Marcos V. Vasluianu, Florin-Alexandru Xiong, Jinhui Ye, Wei Ranjan, Rakesh Timofte, Radu Zheng, Huan Han, Wencheng Yan, Tianyi Shen, Jianbing Sun, Pihai Yao, Yuanqi Jiang, Kui Zhao, Wenbo Liu, Xianming Burnaev, Evgeny Jiang, Junjun Han, Woojae Lee, Kyeonghyun Hong, Seongmin Chun, Se Young Kim, Jinseong Kim, Dohyeong Kim, Jeahwan Wang, Yubo Zhang, Chi Luo, Huizhen Wu, Yansai Huang, Mengcheng Liu, Chengji Yve, Chongli Sun, Jianhang Guo, Cheng Du, Yingcai Jianhao, Huang Shuai, Liu Chenghua, Li Computer Vision Lab CAIDAS IFI University of Würzburg Germany Visual Computing Group FTG Sony PlayStation Meta Reality Labs Challenge Organizers

The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing. Depth maps, essential for rendering realistic scenes and supporting advanced functionalities, are typically large and challenging to stream efficiently due to their size. This challenge introduces a focus on developing innovative depth upsampling techniques to reconstruct high-quality depth maps from compressed data. These techniques are crucial for overcoming the limitations posed by depth compression, which often degrades quality, loses scene details and introduces artifacts. By enhancing depth upsampling methods, this challenge aims to improve the efficiency and quality of depth map reconstruction. Our goal is to advance the state-of-the-art in depth processing technologies, thereby enhancing the overall user experience in AR and VR applications. © 2024, CC BY.

关键词： Augmented reality

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Han, Feng Chen, Kai Gong, Chao Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model’s ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module’s outputs across different layers and timesteps, automatically balancing the erasure effects and model’s generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure (detecting only 34 nude parts), Cartoon Concept Removal (with an average LPIPSda of 0.428, 0.113 higher than SOTA at 0.315), and Artistic Style Erasure (with an average LPIPSda of 0.387, 0.088 higher than SOTA at 0.299), clearly outperforming alternative methods. Code is available at https://***/Maplebb/DuMo Copyright © 2025, The Author

关键词： HTTP

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes

学校读者我要写书评

暂无评论

Unsigned Orthogonal Distance Fields: An Accurate Neural Impl...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yujie Lu Long Want Nayu Ding Yulong Wang Shuhan Shen Shen Cai Lin Gao Visual and Geometric Perception Lab Donghua University Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However, common distance field based implicit represen-tations, specifically signed distance field (SDF) for water-tight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes. In this paper, we introduce a novel neural implicit representation based on unsigned orthogonal distance fields (UODFs). In UODFs, the minimal unsigned distance from any spatial point to the shape surface is de-fined solely in one orthogonal direction, contrasting with the multi-directional determination made by SDF and UDF. Consequently, every point in the 3D UODFs can directly access its closest surface points along three orthogonal di-rections. This distinctive feature leverages the accurate re-construction of surface points without interpolation errors. We verify the effectiveness of UODFs through a range of re-construction examples, extending from simple watertight or non-watertight shapes to complex shapes that include hol-lows, internal or assembling structures.

关键词： Measurement Surface reconstruction Interpolation Three-dimensional displays Accuracy Shape Neural networks

AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Katsavounidis, Ioannis Timofte, Radu Luo, Qing Song, Jie Jiang, Linyan Lei, Haibo Li, Yaqing Luo, Ziqi Dong, Rongkang Yang, Cuixin He, Zongqi Xiao, Jun Xiao, Zhe Zuo, Yushen Lyu, Zihang Lam, Kin-Man Jiang, Yuxuan Nawala, Jakub Feng, Chen Zhang, Fan Zhu, Xiaoqing Sole, Joel Bull, David Lee, Jae-Hyeon Son, Dong-Hyeop Choi, Ui-Jin Zheng, Mingjun Yang, Zhongbao Sun, Long Pan, Jinshan Dong, Jiangxin Tang, Jinhui Conde, Marcos V. Lei, Zhijun Li, Wen Bampis, Christos Computer Vision Lab CAIDAS & IFI University of Würzburg Germany Visual Computing Group FTG Sony PlayStation Meta Video Infrastructure Group Netflix Inc

Video super-resolution (VSR) is a critical task for enhancing low-bitrate and low-resolution videos, particularly in streaming applications. While numerous solutions have been developed, they often suffer from high computational demands, resulting in low frame rates (FPS) and poor power efficiency, especially on mobile platforms. In this work, we compile different methods to address these challenges, the solutions are end-to-end real-time video super-resolution frameworks optimized for both high performance and low runtime. We also introduce a new test set of high-quality 4K videos to further validate the approaches. The proposed solutions tackle video up-scaling for two applications: 540p to 4K (x4) as a general case, and 360p to 1080p (x3) more tailored towards mobile devices. In both tracks, the solutions have a reduced number of parameters and operations (MACs), allow high FPS, and improve VMAF and PSNR over interpolation baselines. This report gauges some of the most efficient video super-resolution methods to date. © 2024, CC BY-NC-ND.

关键词： Video streaming

Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study

学校读者我要写书评

暂无评论

Attention Modules Improve Image-Level Anomaly Detection for ...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： André Luiz Vieira e Silva Francisco Simões Danny Kowerko Tobias Schlosser Felipe Battisti Veronica Teichrieb Voxar Labs Centro de Informática Universidade Federal de Pernambuco Brazil Visual Computing Lab DC Universidade Federal Rural de Pernambuco Brazil Junior Professorship of Media Computing Chemnitz University of Technology Germany

Within (semi-)automated visual industrial inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The emergence of these often rarely occurring defect patterns explains the general need for labeled data corpora. To alleviate this issue and advance the current state of the art in unsupervised visual inspection, this work proposes a DifferNet-based solution enhanced with attention modules: AttentDifferNet. It improves image-level detection and classification capabilities on three visual anomaly detection datasets for industrial inspection: InsPLAD-fault, MVTec AD, and Semiconductor Wafer. In comparison to the state of the art, AttentDifferNet achieves improved results, which are, in turn, highlighted throughout our quali-quantitative study. Our quantitative evaluation shows an average improvement - compared to DifferNet -of 1.77 ± 0.25 percentage points in overall AUROC considering all three datasets, reaching SOTA results in InsPLAD-fault, an industrial inspection in-the-wild dataset. As our variants to AttentDifferNet show great prospects in the context of currently investigated approaches, a baseline is formulated, emphasizing the importance of attention for industrial anomaly detection both in the wild and in controlled environments.

关键词：

UniToken: Harmonizing Multimodal Understanding and Generation through Unified visual Encoding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jiao, Yang Qiu, Haibo Jie, Zequn Chen, Shaoxiang Chen, Jingjing Ma, Lin Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Meituan China

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth experiments, we uncover key principles for developing a unified model capable of both visual understanding and image generation. Extensive evaluations across a diverse range of prominent benchmarks demonstrate that UniToken achieves state-of-the-art performance, surpassing existing approaches. These results establish UniToken as a robust foundation for future research in this domain. The code and models are available at https://***/SxJyJay/UniToken. © 2025, CC BY-NC-SA.

关键词： Knowledge acquisition