Even if Application-Specific Integrated Circuits (ASIC) have proven to be a relevant choice for integrating inference at the edge, they are often limited in terms of applicability. In this paper, we demonstrate that an ASIC neural network accelerator dedicated to image processing can be applied to multiple tasks of different levels: image classification and compression, while requiring a very limited hardware. The key component is a reconfigurable, mixed-precision (3b/2b/1b) encoder that takes advantage of proper weight and activation quantizations combined with convolutional layer structural pruning to lower hardware-related constraints (memory and computing). We introduce an automatic adaptation of linear symmetric quantizer scaling factors to perform quantized levels equalization, aiming at stabilizing quinary and ternary weights training. In addition, a proposed layer-shared Bit-Shift Normalization significantly simplifies the implementation of the hardware-expensive Batch Normalization. For a specific configuration in which the encoder design only requires 1Mb, the classification accuracy reaches 87.5% on CIFAR-10. Besides, we also show that this quantized encoder can be used to compress image patch-by-patch while the reconstruction can performed remotely, by a dedicated full-frame decoder. This solution typically enables an end-to-end compression almost without any block artifacts, outperforming patch-based state-of-the-art techniques employing a patch-constant bitrate.
GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression
Huawei Hong Kong Research Center（华为香港研究中心）；The Hong Kong University of Science and Technology（香港科技大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深港协同创新研究院）
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；HUAWEI Technologies Co., Ltd.（华为技术有限公司）；Peng Cheng Laboratory（鹏城实验室）；Shenzhen University（深圳大学）
除了实现比经典图像压缩编解码器更高的压缩效率之外，深度图像压缩预计将利用附加的边信息来改进，例如，从同一场景的不同角度拍摄的另一张照片。为了更好地利用分布式压缩场景下的边信息，现有方法（Ayzik and Avidan 2020）仅在图像域实现补丁匹配，以解决由视点差异引起的视差问题。然而，图像域的块匹配对不同视角引起的尺度、形状和光照变化鲁棒性差，不能充分利用边信息图像丰富的纹理信息。为了解决这个问题，我们提出了多尺度特征域补丁匹配（MSFRENT），充分利用边信息在分布式图像压缩模型的解码器。具体地说，MSFNN由边信息特征提取器、多尺度特征域块匹配模块和多尺度特征融合网络组成。此外，我们重新利用浅层的区块间相关性来加速深层的区块匹配。最后，我们发现，与图像域的补丁匹配方法相比，我们在多尺度特征域中的补丁匹配进一步提高了约20%的压缩率（Ayzik和Avidan 2020）。
Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform
Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Harbin Institute of Technology（哈尔滨工业大学）
Continuous Patch Stitching for Block-wise Image Compression
School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；School of Electronic and Information Engineering, University of Electronic Science and Technology of China（电子科技大学电子信息工程学院）
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）
Learned Image Compression for HE-stained Histopathological Images via Stain Deconvolution
German Cancer Research Center (DKFZ)（德国癌症研究中心）；German Cancer Consortium (DKTK)（德国癌症联盟）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；Heidelberg University（海德堡大学）；Technical University of Munich（慕尼黑工业大学）
Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal
College of Intelligence and Computing（智能与计算学院）；Tianjin University（天津大学）；School of Cyberspace Science and Technology（网络空间安全学院）；Beijing Institute of Technology（北京理工大学）；National Key Laboratory of Science and Technology on Information System Security（信息系统安全科学与技术国家重点实验室）
RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
School of Electronics, Peking University（北京大学电子学院）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Hong Kong Polytechnic University（香港理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Lab（鹏程实验室）；ETH Zurich（苏黎世联邦理工学院）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs
Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究所）；Department of Biomedical Engineering, Peking University（北京大学生物医学工程系）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）
CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
ERNIE Team, Baidu Inc.（百度公司ERNIE团队）；The Hong Kong University of Science and Technology（香港科技大学）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Deep learning-based compression of giga-resolution whole slide images
Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU)（临床与分子医学系，挪威科学技术大学（NTNU））；Clinic of Laboratory Medicine, St. Olavs hospital, Trondheim University Hospital（实验室医学诊所，圣奥拉夫医院，特罗姆瑟大学医院）；Department of Health Research, SINTEF Digital（健康研究部，SINTEF数字）；Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU)（循环与医学成像系，挪威科学技术大学（NTNU））
An Adaptive Statistical Non-uniform Quantizer for Detail Wavelet Components in Lossy JPEG2000 Image Compression
Cornell University（康奈尔大学）；Indian Institute of Information Technology, Allahabad（阿拉哈巴德印度信息技术学院）；Indian Institute of Science Education and Research - Kolkata（加尔各答印度科学教育与研究学院）
