Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCombining Transformer Generators with Convolutional Discriminators
277
0
0.0
(
0
)
Added by
Ricard Durall Lopez
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis using generative adversarial networks (GANs) has drastically improved over the last few years. The recently proposed TransGAN is the first GAN using only transformer-based architectures and achieves competitive results when compared to convolutional GANs. However, since transformers are data-hungry architectures, TransGAN requires data augmentation, an auxiliary super-resolution task during training, and a masking prior to guide the self-attention mechanism. In this paper, we study the combination of a transformer-based generator and convolutional discriminator and successfully remove the need of the aforementioned required design choices. We evaluate our approach by conducting a benchmark of well-known CNN discriminators, ablate the size of the transformer-based generator, and show that combining both architectural elements into a hybrid model leads to better results. Furthermore, we investigate the frequency spectrum properties of generated images and observe that our model retains the benefits of an attention based generator.
rate research
Read More
We tackle the low-efficiency flaw of vision transformer caused by the high computational/space complexity in Multi-Head Self-Attention (MHSA). To this end, we propose the Hierarchical MHSA (H-MHSA), whose representation is computed in a hierarchical manner. Specifically, our H-MHSA first learns feature relationships within small grids by viewing image patches as tokens. Then, small grids are merged into larger ones, within which feature relationship is learned by viewing each small grid at the preceding step as a token. This process is iterated to gradually reduce the number of tokens. The H-MHSA module is readily pluggable into any CNN architectures and amenable to training via backpropagation. We call this new backbone TransCNN, and it essentially inherits the advantages of both transformer and CNN. Experiments demonstrate that TransCNN achieves state-of-the-art accuracy for image recognition. Code and pretrained models are available at https://github.com/yun-liu/TransCNN. This technical report will keep updating by adding more experiments.
An explicit discriminator trained on observable in-distribution (ID) samples can make high-confidence prediction on out-of-distribution (OOD) samples due to its distributional vulnerability. This is primarily caused by the limited ID samples observable for training discriminators when OOD samples are unavailable. To address this issue, the state-of-the-art methods train the discriminator with OOD samples generated by general assumptions without considering the data and network characteristics. However, different network architectures and training ID datasets may cause diverse vulnerabilities, and the generated OOD samples thus usually misaddress the specific distributional vulnerability of the explicit discriminator. To reveal and patch the distributional vulnerabilities, we propose a novel method of textit{fine-tuning explicit discriminators by implicit generators} (FIG). According to the Shannon entropy, an explicit discriminator can construct its corresponding implicit generator to generate specific OOD samples without extra training costs. A Langevin Dynamic sampler then draws high-quality OOD samples from the generator to reveal the vulnerability. Finally, a regularizer, constructed according to the design principle of the implicit generator, patches the distributional vulnerability by encouraging those generated OOD samples with high entropy. Our experiments on four networks, four ID datasets and seven OOD datasets demonstrate that FIG achieves state-of-the-art OOD detection performance and maintains a competitive classification capability.
Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just counting numbers for the whole crowd scene, which brings greater challenges, especially in extremely congested crowd scenes. In this paper, we focus on how to achieve precise instance localization in high-density crowd scenes, and to alleviate the problem that the feature extraction ability of the traditional model is reduced due to the target occlusion, the image blur, etc. To this end, we propose a Dilated Convolutional Swin Transformer (DCST) for congested crowd scenes. Specifically, a window-based vision transformer is introduced into the crowd localization task, which effectively improves the capacity of representation learning. Then, the well-designed dilated convolutional module is inserted into some different stages of the transformer to enhance the large-range contextual information. Extensive experiments evidence the effectiveness of the proposed methods and achieve state-of-the-art performance on five popular datasets. Especially, the proposed model achieves F1-measure of 77.5% and MAE of 84.2 in terms of localization and counting performance, respectively.
Existing image captioning methods just focus on understanding the relationship between objects or instances in a single image, without exploring the contextual correlation existed among contextual image. In this paper, we propose Dual Graph Convolutional Networks (Dual-GCN) with transformer and curriculum learning for image captioning. In particular, we not only use an object-level GCN to capture the object to object spatial relation within a single image, but also adopt an image-level GCN to capture the feature information provided by similar images. With the well-designed Dual-GCN, we can make the linguistic transformer better understand the relationship between different objects in a single image and make full use of similar images as auxiliary information to generate a reasonable caption description for a single image. Meanwhile, with a cross-review strategy introduced to determine difficulty levels, we adopt curriculum learning as the training strategy to increase the robustness and generalization of our proposed model. We conduct extensive experiments on the large-scale MS COCO dataset, and the experimental results powerfully demonstrate that our proposed method outperforms recent state-of-the-art approaches. It achieves a BLEU-1 score of 82.2 and a BLEU-2 score of 67.6. Our source code is available at {em color{magenta}{url{https://github.com/Unbear430/DGCN-for-image-captioning}}}.
This paper has been withdrawn by the author(s),
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
