Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this problem. We first pinpoint task-aware regions over the input image by a lightweight patch proposal network called AnchorNet. We then feed these localized semantic patches with much smaller spatial redundancy into a general classification network. Unlike the popular design of deep CNN, we aim to carefully design the Receptive Field of AnchorNet without intermediate convolutional paddings. This ensures the exact mapping from a high-level spatial location to the specific input image patch. The contribution of each patch is interpretable. Moreover, AnchorNet is compatible with any downstream architecture. Experimental results on ImageNet show that our method outperforms SOTA dynamic inference methods with fewer inference costs. Our code is available at https://github.com/winycg/AnchorNet.
We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. We learn representations by classifying normal data from the CutPaste, a simple data augmentation strategy that cuts an image patch and pastes at a random location of a large image. Our empirical study on MVTec anoma…
We introduce the notion of a Patch Sampling Schedule (PSS), that varies the number of Vision Transformer (ViT) patches used per batch during training. Since all patches are not equally important for most vision objectives (e.g., classification), we argue that less important patches can be used in fewer training iterations, leading to shorter training time with minimal impact on performance. Additionally, we observe that training with a PSS makes a ViT more robust to a wider patch sampling range during inference. This allows for a fine-grained, dynamic trade-off between throughput and accuracy …
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学PCA实验室）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学PCA实验室）
Detection and Localization of Image Forgeries using Resampling Features and Deep Learning
Mayachitra Inc.（Mayachitra公司）；University of California, Riverside（加州大学河滨分校）；Naval Air Warfare Center Weapons Division（海军航空作战中心武器部）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving cars. Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images. An object detector classifies and predicts the types of objects within an image, such as by distinguishing a motorcyclist from the mo…
Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100$\times$ speed-up
University of California, San Diego（加州大学圣迭戈分校）；IMB, CNRS, Univ. Bordeaux, Bordeaux INP（波尔多大学，法国国家科学研究中心，波尔多综合理工学院）；Univ Lyon, UJM-Saint-Etienne, CNRS, Institut d Optique Graduate School, Laboratoire Hubert Curien UMR 5516（里昂大学，圣埃蒂安让·莫奈大学，法国国家科学研究中心，光学研究生院，于贝尔·居里安实验室）
Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models
Convergence Research Institute, Sungkyunkwan University（convergence research institute, 首尔大学）；School of Information Technology, Deakin University（信息科技学院, 德金大学）；Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系, 首尔大学）
Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant co…
Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
School of Computer Science（计算机科学学院）；Technology, Xi’an Jiaotong University, Xi’an, China（技术学院，西安交通大学，西安，中国）；Department of Transmedia Art, Xi’an Academy of Fine Arts, Xi’an, China（多媒体艺术系，西安美术学院，西安，中国）；Department of Oncology, University of Cambridge, Cambridge, U.K.（肿瘤学系，剑桥大学，剑桥，英国）；Language Technology Lab, University of Cambridge, Cambridge, U.K.（语言技术实验室，剑桥大学，剑桥，英国）；Institute of High Performance Computing, Agency for Science, Technology（高性能计算研究所，科技研究局）
Huazhong University of Science and Technology（华中科技大学）；Tencent Youtu Lab（腾讯优图实验室）
Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we prop…
Patch-Based and Non-Patch-Based inputs Comparison into Deep Neural Models: Application for the Segmentation of Retinal Diseases on Optical Coherence Tomography Volumes
Laboratoire LIMOS, CNRS UMR 6158（利摩日大学实验室，法国国家科研中心UMR 6158联合研究单位）；Université Clermont-Auvergne（克莱蒙奥弗涅大学）；AL Mansour University College（曼苏尔大学学院）
