LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 21

Search options

  1. Book ; Online: Augmenting Sub-model to Improve Main Model

    Heo, Byeongho / Kim, Taekyung / Yun, Sangdoo / Han, Dongyoon

    2023  

    Abstract: Image classification has improved with the development of training techniques. However, these techniques often require careful parameter tuning to balance the strength of regularization, limiting their potential benefits. In this paper, we propose a ... ...

    Abstract Image classification has improved with the development of training techniques. However, these techniques often require careful parameter tuning to balance the strength of regularization, limiting their potential benefits. In this paper, we propose a novel way to use regularization called Augmenting Sub-model (AugSub). AugSub consists of two models: the main model and the sub-model. While the main model employs conventional training recipes, the sub-model leverages the benefit of additional regularization. AugSub achieves this by mitigating adverse effects through a relaxed loss function similar to self-distillation loss. We demonstrate the effectiveness of AugSub with three drop techniques: dropout, drop-path, and random masking. Our analysis shows that all AugSub improves performance, with the training loss converging even faster than regular training. Among the three, AugMask is identified as the most practical method due to its performance and cost efficiency. We further validate AugMask across diverse training recipes, including DeiT-III, ResNet, MAE fine-tuning, and Swin Transformer. The results show that AugMask consistently provides significant performance gain. AugSub provides a practical and effective solution for introducing additional regularization under various training recipes. Code is available at \url{https://github.com/naver-ai/augsub}.

    Comment: 15 pages, 3 figures
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2023-06-20
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: Masked Image Modeling via Dynamic Token Morphing

    Kim, Taekyung / Han, Dongyoon / Heo, Byeongho

    2023  

    Abstract: Masked Image Modeling (MIM) arises as a promising option for Vision Transformers among various self-supervised learning (SSL) methods. The essence of MIM lies in token-wise masked patch predictions, with targets patchified from images; or generated by ... ...

    Abstract Masked Image Modeling (MIM) arises as a promising option for Vision Transformers among various self-supervised learning (SSL) methods. The essence of MIM lies in token-wise masked patch predictions, with targets patchified from images; or generated by pre-trained tokenizers or models. We argue targets from the pre-trained models usually exhibit spatial inconsistency, which makes it excessively challenging for the model to follow to learn more discriminative representations. To mitigate the issue, we introduce a novel self-supervision signal based on Dynamic Token Morphing (DTM), which dynamically aggregates contextually related tokens. DTM can be generally applied to various SSL frameworks, yet we propose a simple MIM that employs DTM to effectively improve the performance barely introducing extra training costs. Our experiments on ImageNet-1K and ADE20K evidently demonstrate the superiority of our methods. Furthermore, the comparative evaluation of iNaturalist and Fine-grained Visual Classification datasets further validates the transferability of our method on various downstream tasks. Our code will be released publicly.

    Comment: 15 pages, 6 figures
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2023-12-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Article ; Online: Rollback Ensemble With Multiple Local Minima in Fine-Tuning Deep Learning Networks.

    Ro, Youngmin / Choi, Jongwon / Heo, Byeongho / Choi, Jin Young

    IEEE transactions on neural networks and learning systems

    2022  Volume 33, Issue 9, Page(s) 4648–4660

    Abstract: Image retrieval is a challenging problem that requires learning generalized features enough to identify untrained classes, even with very few classwise training samples. In this article, to obtain generalized features further in learning retrieval data ... ...

    Abstract Image retrieval is a challenging problem that requires learning generalized features enough to identify untrained classes, even with very few classwise training samples. In this article, to obtain generalized features further in learning retrieval data sets, we propose a novel fine-tuning method of pretrained deep networks. In the retrieval task, we discovered a phenomenon in which the loss reduction in fine-tuning deep networks is stagnated, even while weights are largely updated. To escape from the stagnated state, we propose a new fine-tuning strategy to roll back some of the weights to the pretrained values. The rollback scheme is observed to drive the learning path to a gentle basin that provides more generalized features than a sharp basin. In addition, we propose a multihead ensemble structure to create synergy among multiple local minima obtained by our rollback scheme. Experimental results show that the proposed learning method significantly improves generalization performance, achieving state-of-the-art performance on the Inshop and SOP data sets.
    Language English
    Publishing date 2022-08-31
    Publishing country United States
    Document type Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2021.3059669
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Book ; Online: SeiT

    Park, Song / Chun, Sanghyuk / Heo, Byeongho / Kim, Wonjae / Yun, Sangdoo

    Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

    2023  

    Abstract: We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with ... ...

    Abstract We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with unlimited dataset storage with limited storage infrastructure. A number of storage-efficient training methods have been proposed to tackle the problem, but they are rarely scalable or suffer from severe damage to performance. In this paper, we propose a storage-efficient training strategy for vision classifiers for large-scale datasets (e.g., ImageNet) that only uses 1024 tokens per instance without using the raw level pixels; our token storage only needs <1% of the original JPEG-compressed raw pixels. We also propose token augmentations and a Stem-adaptor module to make our approach able to use the same architecture as pixel-based approaches with only minimal modifications on the stem layer and the carefully tuned optimization settings. Our experimental results on ImageNet-1k show that our method significantly outperforms other storage-efficient training methods with a large gap. We further show the effectiveness of our method in other practical scenarios, storage-efficient pre-training, and continual learning. Code is available at https://github.com/naver-ai/seit

    Comment: ICCV 2023; First two authors contributed equally; code url: https://github.com/naver-ai/seit; 17 pages, 1.2MB
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2023-03-20
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: What Do Self-Supervised Vision Transformers Learn?

    Park, Namuk / Kim, Wonjae / Heo, Byeongho / Kim, Taekyung / Yun, Sangdoo

    2023  

    Abstract: We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision Transformers ( ... ...

    Abstract We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision Transformers (ViTs) have the following properties: (1) CL trains self-attentions to capture longer-range global patterns than MIM, such as the shape of an object, especially in the later layers of the ViT architecture. This CL property helps ViTs linearly separate images in their representation spaces. However, it also makes the self-attentions collapse into homogeneity for all query tokens and heads. Such homogeneity of self-attention reduces the diversity of representations, worsening scalability and dense prediction performance. (2) CL utilizes the low-frequency signals of the representations, but MIM utilizes high-frequencies. Since low- and high-frequency information respectively represent shapes and textures, CL is more shape-oriented and MIM more texture-oriented. (3) CL plays a crucial role in the later layers, while MIM mainly focuses on the early layers. Upon these analyses, we find that CL and MIM can complement each other and observe that even the simplest harmonization can help leverage the advantages of both methods. The code is available at https://github.com/naver-ai/cl-vs-mim.

    Comment: ICLR 2023
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning
    Subject code 170
    Publishing date 2023-05-01
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Book ; Online: Forging Tokens for Improved Storage-efficient Training

    Lee, Minhyun / Park, Song / Heo, Byeongho / Han, Dongyoon / Shim, Hyunjung

    2023  

    Abstract: Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires extensive datasets, leading to large storage ... ...

    Abstract Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires extensive datasets, leading to large storage requirements. This storage challenge poses a critical bottleneck for scaling up vision models. Motivated by the success of discrete representations, SeiT proposes to use Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. However, applying traditional data augmentations to tokens faces challenges due to input domain shift. To address this issue, we introduce TokenAdapt and ColorAdapt, simple yet effective token-based augmentation strategies. TokenAdapt realigns token embedding space for compatibility with spatial augmentations, preserving the model's efficiency without requiring fine-tuning. Additionally, ColorAdapt addresses color-based augmentations for tokens inspired by Adaptive Instance Normalization (AdaIN). We evaluate our approach across various scenarios, including storage-efficient ImageNet-1k classification, fine-grained classification, robustness benchmarks, and ADE-20k semantic segmentation. Experimental results demonstrate consistent performance improvement in diverse experiments. Code is available at https://github.com/naver-ai/tokenadapt.

    Comment: First two authors contributed equally
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Publishing date 2023-12-14
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Book ; Online: Match me if you can

    Kim, Jiwon / Heo, Byeongho / Yun, Sangdoo / Kim, Seungryong / Han, Dongyoon

    Semantic Correspondence Learning with Unpaired Images

    2023  

    Abstract: Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points. Despite their performance improvements, they remain constrained by the ... ...

    Abstract Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points. Despite their performance improvements, they remain constrained by the limited training pairs due to costly point-level annotations. This paper proposes a simple yet effective method that performs training with unlabeled pairs to complement both limited image pairs and sparse point pairs, requiring neither extra labeled keypoints nor trainable modules. We fundamentally extend the data quantity and variety by augmenting new unannotated pairs not primitively provided as training pairs in benchmarks. Using a simple teacher-student framework, we offer reliable pseudo correspondences to the student network via machine supervision. Finally, the performance of our network is steadily improved by the proposed iterative training, putting back the student as a teacher to generate refined labels and train a new student repeatedly. Our models outperform the milestone baselines, including state-of-the-art methods on semantic correspondence benchmarks.

    Comment: 12 pages
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2023-11-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Book ; Online: Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation

    Nam, Giung / Lee, Hyungi / Heo, Byeongho / Lee, Juho

    2022  

    Abstract: Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates distilling knowledge from the ensemble teacher into a smaller student ... ...

    Abstract Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates distilling knowledge from the ensemble teacher into a smaller student network, and there are two important design choices for this ensemble distillation: 1) how to construct the student network, and 2) what data should be shown during training. In this paper, we propose a weight averaging technique where a student with multiple subnetworks is trained to absorb the functional diversity of ensemble teachers, but then those subnetworks are properly averaged for inference, giving a single student network with no additional inference cost. We also propose a perturbation strategy that seeks inputs from which the diversities of teachers can be better transferred to the student. Combining these two, our method significantly improves upon previous methods on various image classification tasks.

    Comment: ICML 2022
    Keywords Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-06-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Book ; Online: Joint Global and Local Hierarchical Priors for Learned Image Compression

    Kim, Jun-Hyuk / Heo, Byeongho / Lee, Jong-Seok

    2021  

    Abstract: Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like ... ...

    Abstract Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent representation. Like other vision tasks, most recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling long-range dependencies due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To overcome this issue, we propose a novel entropy model called Information Transformer (Informer) that exploits both global and local information in a content-dependent manner using an attention mechanism. Our experiments show that Informer improves rate--distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem. Our source code is available at https://github.com/naver-ai/informer.

    Comment: CVPR 2022
    Keywords Electrical Engineering and Systems Science - Image and Video Processing ; Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2021-12-08
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Book ; Online: Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching

    Ji, Mingi / Heo, Byeongho / Park, Sungrae

    2021  

    Abstract: Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge through pre-defined ...

    Abstract Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge through pre-defined links. However, manual selection often constructs ineffective links that limit the improvement from the distillation. There has been an attempt to address the problem, but it is still challenging to identify effective links under practical scenarios. In this paper, we introduce an effective and efficient feature distillation method utilizing all the feature levels of the teacher without manually selecting the links. Specifically, our method utilizes an attention-based meta-network that learns relative similarities between features, and applies identified similarities to control distillation intensities of all possible pairs. As a result, our method determines competent links more efficiently than the previous approach and provides better performance on model compression and transfer learning tasks. Further qualitative analyses and ablative studies describe how our method contributes to better distillation. The implementation code is available at github.com/clovaai/attention-feature-distillation.

    Comment: 10 page, AAAI 2021
    Keywords Computer Science - Machine Learning
    Subject code 004
    Publishing date 2021-02-04
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top