2023-09-28 更新
DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion
Authors:Zhenzhen Chu, Jiayu Chen, Cen Chen, Chengyu Wang, Ziheng Wu, Jun Huang, Weining Qian
Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of various structures of ViTs, ViTs are increasingly advantageous for many vision tasks. However, the quadratic complexity of self-attention renders ViTs computationally intensive, and their lack of inductive biases of locality and translation equivariance demands larger model sizes compared to CNNs to effectively learn visual features. In this paper, we propose a light-weight and efficient vision transformer model called DualToken-ViT that leverages the advantages of CNNs and ViTs. DualToken-ViT effectively fuses the token with local information obtained by convolution-based structure and the token with global information obtained by self-attention-based structure to achieve an efficient attention structure. In addition, we use position-aware global tokens throughout all stages to enrich the global information, which further strengthening the effect of DualToken-ViT. Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks. We conducted extensive experiments on image classification, object detection and semantic segmentation tasks to demonstrate the effectiveness of DualToken-ViT. On the ImageNet-1K dataset, our models of different scales achieve accuracies of 75.4% and 79.4% with only 0.5G and 1.0G FLOPs, respectively, and our model with 1.0G FLOPs outperforms LightViT-T using global tokens by 0.7%.
PDF
点此查看论文截图
Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation
Authors:Bonifaz Stuhr, Jürgen Brauer, Bernhard Schick, Jordi Gonzàlez
A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images while mimicking the style of the target domain. Due to biases between the datasets of both domains, many methods suffer from inconsistencies caused by the translation process. Most approaches introduced to mitigate these inconsistencies do not constrain the discriminator, leading to an even more ill-posed training setup. Moreover, none of these approaches is designed for larger crop sizes. In this work, we show that masking the inputs of a global discriminator for both domains with a content-based mask is sufficient to reduce content inconsistencies significantly. However, this strategy leads to artifacts that can be traced back to the masking process. To reduce these artifacts, we introduce a local discriminator that operates on pairs of small crops selected with a similarity sampling strategy. Furthermore, we apply this sampling strategy to sample global input crops from the source and target dataset. In addition, we propose feature-attentive denormalization to selectively incorporate content-based statistics into the generator stream. In our experiments, we show that our method achieves state-of-the-art performance in photorealistic sim-to-real translation and weather translation and also performs well in day-to-night translation. Additionally, we propose the cKVD metric, which builds on the sKVD metric and enables the examination of translation quality at the class or category level.
PDF 24 pages, 22 figures, under review
点此查看论文截图
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation
Authors:Ke Fan, Jingshi Lei, Xuelin Qian, Miaopeng Yu, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu
Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some studies have achieved promising performance by using motion flow to integrate information across frames under a self-supervised setting. However, motion flow has a clear limitation by the two factors of moving cameras and object deformation. This paper presents a rethinking to previous works. We particularly leverage the supervised signals with object-centric representation in \textit{real-world scenarios}. The underlying idea is the supervision signal of the specific object and the features from different views can mutually benefit the deduction of the full mask in any specific frame. We thus propose an Efficient object-centric Representation amodal Segmentation (EoRaS). Specially, beyond solely relying on supervision signals, we design a translation module to project image features into the Bird’s-Eye View (BEV), which introduces 3D information to improve current feature quality. Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion. As a result, the full mask of the object can be decoded from image features updated by object slots. Extensive experiments on both real-world and synthetic benchmarks demonstrate the superiority of our proposed method, achieving state-of-the-art performance. Our code will be released at \url{https://github.com/kfan21/EoRaS}.
PDF Accepted by ICCV 2023
点此查看论文截图
Efficient Post-training Quantization with FP8 Formats
Authors:Haihao Shen, Naveen Mellempudi, Xin He, Qun Gao, Chang Wang, Mengni Wang
Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this goal, we study the advantages of FP8 data formats for post-training quantization across 75 unique network architectures covering a wide range of tasks, including machine translation, language modeling, text generation, image classification, generation, and segmentation. We examine three different FP8 representations (E5M2, E4M3, and E3M4) to study the effects of varying degrees of trade-off between dynamic range and precision on model accuracy. Based on our extensive study, we developed a quantization workflow that generalizes across different network architectures. Our empirical results show that FP8 formats outperform INT8 in multiple aspects, including workload coverage (92.64% vs. 65.87%), model accuracy and suitability for a broader range of operations. Furthermore, our findings suggest that E4M3 is better suited for NLP models, whereas E3M4 performs marginally better than E4M3 on computer vision tasks. The code is publicly available on Intel Neural Compressor: https://github.com/intel/neural-compressor.
PDF
点此查看论文截图
CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration
Authors:Shuhao Kang, Youqi Liao, Jianping Li, Fuxun Liang, Yuhao Li, Fangning Li, Zhen Dong, Bisheng Yang
Image-to-point cloud (I2P) registration is a fundamental task in the fields of robot navigation and mobile mapping. Existing I2P registration works estimate correspondences at the point-to-pixel level, neglecting the global alignment. However, I2P matching without high-level guidance from global constraints may converge to the local optimum easily. To solve the problem, this paper proposes CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner for the global optimal solution. First, the image and point cloud are fed into a Siamese encoder-decoder network for hierarchical feature extraction. Then, a coarse-to-fine matching module is designed to exploit features and establish resilient feature correspondences. Specifically, in the coarse matching block, a novel I2P transformer module is employed to capture the homogeneous and heterogeneous global information from image and point cloud. With the discriminate descriptors, coarse super-point-to-super-pixel matching pairs are estimated. In the fine matching module, point-to-pixel pairs are established with the super-point-to-super-pixel correspondence supervision. Finally, based on matching pairs, the transform matrix is estimated with the EPnP-RANSAC algorithm. Extensive experiments conducted on the KITTI dataset have demonstrated that CoFiI2P achieves a relative rotation error (RRE) of 2.25 degrees and a relative translation error (RTE) of 0.61 meters. These results represent a significant improvement of 14% in RRE and 52% in RTE compared to the current state-of-the-art (SOTA) method. The demo video for the experiments is available at https://youtu.be/TG2GBrJTuW4. The source code will be public at https://github.com/kang-1-2-3/CoFiI2P.
PDF demo video: https://youtu.be/TG2GBrJTuW4 source code: https://github.com/kang-1-2-3/CoFiI2P
点此查看论文截图
Uncertainty Quantification via Neural Posterior Principal Components
Authors:Elias Nehme, Omer Yair, Tomer Michaeli
Uncertainty quantification is crucial for the deployment of image restoration models in safety-critical domains, like autonomous driving and biological imaging. To date, methods for uncertainty visualization have mainly focused on per-pixel estimates. However, a heatmap of per-pixel variances is typically of little practical use, as it does not capture the strong correlations between pixels. A more natural measure of uncertainty corresponds to the variances along the principal components (PCs) of the posterior distribution. Theoretically, the PCs can be computed by applying PCA on samples generated from a conditional generative model for the input image. However, this requires generating a very large number of samples at test time, which is painfully slow with the current state-of-the-art (diffusion) models. In this work, we present a method for predicting the PCs of the posterior distribution for any input image, in a single forward pass of a neural network. Our method can either wrap around a pre-trained model that was trained to minimize the mean square error (MSE), or can be trained from scratch to output both a predicted image and the posterior PCs. We showcase our method on multiple inverse problems in imaging, including denoising, inpainting, super-resolution, and biological image-to-image translation. Our method reliably conveys instance-adaptive uncertainty directions, achieving uncertainty quantification comparable with posterior samplers while being orders of magnitude faster. Examples are available at https://eliasnehme.github.io/NPPC/
PDF Accepted to NeurIPS 2023, webpage at https://eliasnehme.github.io/NPPC/
点此查看论文截图