Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHierarchical Spatial Transformer Network
139
0
0.0
(
0
)
Added by
Chang Shu
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Computer vision researchers have been expecting that neural networks have spatial transformation ability to eliminate the interference caused by geometric distortion for a long time. Emergence of spatial transformer network makes dream come true. Spatial transformer network and its variants can handle global displacement well, but lack the ability to deal with local spatial variance. Hence how to achieve a better manner of deformation in the neural network has become a pressing matter of the moment. To address this issue, we analyze the advantages and disadvantages of approximation theory and optical flow theory, then we combine them to propose a novel way to achieve image deformation and implement it with a hierarchical convolutional neural network. This new approach solves for a linear deformation along with an optical flow field to model image deformation. In the experiments of cluttered MNIST handwritten digits classification and image plane alignment, our method outperforms baseline methods by a large margin.
rate research
Read More
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extract the most significant top-K patches, and feeds these patches to a task-specific network -- e.g., auto-encoder or classifier -- to solve a domain specific problem. The challenge in training such a network is the non-differentiable top-K selection process. To address this issue, we lift the training optimization problem by treating the result of top-K selection as a slack variable, resulting in a simple, yet effective, multi-stage training. Our method is able to learn to detect recurrent structures in the training dataset by learning to reconstruct images. It can also learn to localize structures when only knowledge on the occurrence of the object is provided, and in doing so it outperforms the state-of-the-art.
Predicting motion of surrounding agents is critical to real-world applications of tactical path planning for autonomous driving. Due to the complex temporal dependencies and social interactions of agents, on-line trajectory prediction is a challenging task. With the development of attention mechanism in recent years, transformer model has been applied in natural language sequence processing first and then image processing. In this paper, we present a Spatial-Channel Transformer Network for trajectory prediction with attention functions. Instead of RNN models, we employ transformer model to capture the spatial-temporal features of agents. A channel-wise module is inserted to measure the social interaction between agents. We find that the Spatial-Channel Transformer Network achieves promising results on real-world trajectory prediction datasets on the traffic scenes.
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.
This paper presents VTN, a transformer-based framework for video recognition. Inspired by recent developments in vision transformers, we ditch the standard approach in video action recognition that relies on 3D ConvNets and introduce a method that classifies actions by attending to the entire video sequence information. Our approach is generic and builds on top of any given 2D spatial network. In terms of wall runtime, it trains $16.1times$ faster and runs $5.1times$ faster during inference while maintaining competitive accuracy compared to other state-of-the-art methods. It enables whole video analysis, via a single end-to-end pass, while requiring $1.5times$ fewer GFLOPs. We report competitive results on Kinetics-400 and present an ablation study of VTN properties and the trade-off between accuracy and inference speed. We hope our approach will serve as a new baseline and start a fresh line of research in the video recognition domain. Code and models are available at: https://github.com/bomri/SlowFast/blob/master/projects/vtn/README.md
In this paper, we establish a theoretical connection between the classical Lucas & Kanade (LK) algorithm and the emerging topic of Spatial Transformer Networks (STNs). STNs are of interest to the vision and learning communities due to their natural ability to combine alignment and classification within the same theoretical framework. Inspired by the Inverse Compositional (IC) variant of the LK algorithm, we present Inverse Compositional Spatial Transformer Networks (IC-STNs). We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity; in particular, we show superior performance in pure image alignment tasks as well as joint alignment/classification problems on real-world problems.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
