Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInterpretable Structure-Evolving LSTM
95
0
0.0
(
0
)
Added by
Xiaodan Liang
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper develops a general framework for learning interpretable data representation via Long Short-Term Memory (LSTM) recurrent neural networks over hierarchal graph structures. Instead of learning LSTM models over the pre-fixed structures, we propose to further learn the intermediate interpretable multi-level graph structures in a progressive and stochastic way from data during the LSTM network optimization. We thus call this model the structure-evolving LSTM. In particular, starting with an initial element-level graph representation where each node is a small data element, the structure-evolving LSTM gradually evolves the multi-level graph representations by stochastically merging the graph nodes with high compatibilities along the stacked LSTM layers. In each LSTM layer, we estimate the compatibility of two connected nodes from their corresponding LSTM gate outputs, which is used to generate a merging probability. The candidate graph structures are accordingly generated where the nodes are grouped into cliques with their merging probabilities. We then produce the new graph structure with a Metropolis-Hasting algorithm, which alleviates the risk of getting stuck in local optimums by stochastic sampling with an acceptance probability. Once a graph structure is accepted, a higher-level graph is then constructed by taking the partitioned cliques as its nodes. During the evolving process, representation becomes more abstracted in higher-levels where redundant information is filtered out, allowing more efficient propagation of long-range data dependencies. We evaluate the effectiveness of structure-evolving LSTM in the application of semantic object parsing and demonstrate its advantage over state-of-the-art LSTM models on standard benchmarks.
rate research
Read More
How do the neural networks distinguish two images? It is of critical importance to understand the matching mechanism of deep models for developing reliable intelligent systems for many risky visual applications such as surveillance and access control. However, most existing deep metric learning methods match the images by comparing feature vectors, which ignores the spatial structure of images and thus lacks interpretability. In this paper, we present a deep interpretable metric learning (DIML) method for more transparent embedding learning. Unlike conventional metric learning methods based on feature vector comparison, we propose a structural matching strategy that explicitly aligns the spatial embeddings by computing an optimal matching flow between feature maps of the two images. Our method enables deep models to learn metrics in a more human-friendly way, where the similarity of two images can be decomposed to several part-wise similarities and their contributions to the overall similarity. Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods. We evaluate our method on three major benchmarks of deep metric learning including CUB200-2011, Cars196, and Stanford Online Products, and achieve substantial improvements over popular metric learning methods with better interpretability. Code is available at https://github.com/wl-zhao/DIML
Pedestrian trajectory prediction for surveillance video is one of the important research topics in the field of computer vision and a key technology of intelligent surveillance systems. Social relationship among pedestrians is a key factor influencing pedestrian walking patterns but was mostly ignored in the literature. Pedestrians with different social relationships play different roles in the motion decision of target pedestrian. Motivated by this idea, we propose a Social Relationship Attention LSTM (SRA-LSTM) model to predict future trajectories. We design a social relationship encoder to obtain the representation of their social relationship through the relative position between each pair of pedestrians. Afterwards, the social relationship feature and latent movements are adopted to acquire the social relationship attention of this pair of pedestrians. Social interaction modeling is achieved by utilizing social relationship attention to aggregate movement information from neighbor pedestrians. Experimental results on two public walking pedestrian video datasets (ETH and UCY), our model achieves superior performance compared with state-of-the-art methods. Contrast experiments with other attention methods also demonstrate the effectiveness of social relationship attention.
Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms for the processing of images. However the configuration and training of these networks is a complex task requiring deep domain knowledge, experience and much trial and error. Using genetic algorithms, competitive CNN topologies for image recognition can be produced for any specific purpose, however in previous work this has come at high computational cost. In this work two novel approaches are presented to the utilisation of these algorithms, effective in reducing complexity and training time by nearly 20%. This is accomplished via regularisation directly on training time, and the use of partial training to enable early ranking of individual architectures. Both approaches are validated on the benchmark CIFAR10 data set, and maintain accuracy.
In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts between the classes thanks to our data-dependent merge-pruning. Moreover, the prototypes are more consistent and the model is more robust to image perturbations than the state of the art method ProtoPNet. We verify our findings on two datasets, the CUB-200-2011 and the Stanford Cars.
All current non-rigid structure from motion (NRSfM) algorithms are limited with respect to: (i) the number of images, and (ii) the type of shape variability they can handle. This has hampered the practical utility of NRSfM for many applications within vision. In this paper we propose a novel deep neural network to recover camera poses and 3D points solely from an ensemble of 2D image coordinates. The proposed neural network is mathematically interpretable as a multi-layer block sparse dictionary learning problem, and can handle problems of unprecedented scale and shape complexity. Extensive experiments demonstrate the impressive performance of our approach where we exhibit superior precision and robustness against all available state-of-the-art works. The considerable model capacity of our approach affords remarkable generalization to unseen data. We propose a quality measure (based on the network weights) which circumvents the need for 3D ground-truth to ascertain the confidence we have in the reconstruction. Once the networks weights are estimated (for a non-rigid object) we show how our approach can effectively recover 3D shape from a single image -- outperforming comparable methods that rely on direct 3D supervision.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
