Towards End-to-End Image Compression and Analysis with Transformers

Authors: Yuanchao Bai, Xu Yang, Xianming Liu, Junjun Jiang, Yaowei Wang, Xiangyang Ji, Wen Gao104-112

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the effectiveness of the proposed model in both the image compression and the classification tasks. We perform extensive experiments on the Image Net dataset (Deng et al. 2009) and i Naturalist19 (INat19) dataset (Horn and Aodha 2019).
Researcher Affiliation Collaboration 1Harbin Institute of Technology, 2Peng Cheng Laboratory, 3Tsinghua University, 4Peking University
Pseudocode No The paper provides network architecture diagrams and mathematical formulations but does not include explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statement about releasing source code for the methodology, nor does it provide a link to a code repository.
Open Datasets Yes We perform extensive experiments on the Image Net dataset (Deng et al. 2009) and i Naturalist19 (INat19) dataset (Horn and Aodha 2019).
Dataset Splits Yes Image Net is well-known image classification dataset containing 1000 object classes with 1, 281, 167 training images and 50, 000 validation images. INat19 is a fine-grained classification dataset containing 1010 species of plants and animals with 265, 213 training images and 3030 validation images.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, or cloud computing instance types used for running the experiments.
Software Dependencies No The paper mentions optimizers like Adam W and Adam but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We set the input size to 224 224 and adopt the same data augmentation as Dei T (Touvron et al. 2021)... On the Image Net dataset, we train the proposed network from scratch. We use Adam W optimizer (Loshchilov and Hutter 2019) for 300 epochs with minibatches of size 1024. We set the initial learning rate to 0.001 and use a cosine decay learning rate scheduler with 5 epochs warm-up.