Italy

Model efficiency for object detection has become more and more important recently, especially when intelligent mobile devices get more and more popular. Current lightweight object detection model is either migrated from lightweight classification models, or pruned directly from complex object detection models. These pipelines can not match the performance requirements of edge devices. In this work, we propose a neural architecture search (NAS) method to build a detection model automatically that can perform well on edge devices. Specifically, the proposed method supports the search of not only multi-scale feature network, but also backbone network. This enables us to search out a global optimal model. To this end, we&#39;ve made a special design that the backbone and feature network can share the same search space. This method greatly reduces the search time while ensuring the search accuracy. It can find a good architecture in 14GPU days. Additionally, we add latency information into the main objective during performance estimation. Therefore, we can control between the speed and accuracy to better adapt to the edge environment. Experiments on the PASCAL VOC benchmark indicate that the searched architecture (named NAS-EOD) can get good accuracy even if training from scratch. When using a pre-training scheme, our model is superior to state-of-the-art small object detection models.

ICPR 2020

NAS-EOD: an end-to-end Neural Architecture Search method 
for Efficient Object Detection

backbone network

multi-scale feature

efficient object detection

neural architecture search

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


Model efficiency for object detection has become more and more important recently, especially when intelligent mobile devices get more and more popular. Current lightweight object detection model is either migrated from lightweight classification models, or pruned directly from complex object detection models. These pipelines can not match the performance requirements of edge devices. In this work, we propose a neural architecture search (NAS) method to build a detection model automatically that can perform well on edge devices. Specifically, the proposed method supports the search of not only multi-scale feature network, but also backbone network. This enables us to search out a global optimal model. To this end, we've made a special design that the backbone and feature network can share the same search space. This method greatly reduces the search time while ensuring the search accuracy. It can find a good architecture in 14GPU days. Additionally, we add latency information into the main objective during performance estimation. Therefore, we can control between the speed and accuracy to better adapt to the edge environment. Experiments on the PASCAL VOC benchmark indicate that the searched architecture (named NAS-EOD) can get good accuracy even if training from scratch. When using a pre-training scheme, our model is superior to state-of-the-art small object detection models.

poster

Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance. In order to recognize abnormal events such as traffic accidents in a video sequence, it is important that the network takes into account interactions of objects in a given frame. We propose a novel Feature Aggregation (FA) block that refines each object’s features by computing a weighted sum of the features of all objects in a frame. We use FA block along with Long Short Term Memory (LSTM) network to anticipate accidents in the video sequences. We report mean Average Precision (mAP) and Average Time-to-Accident (ATTA) on Street Accident (SA) dataset. Our proposed method achieves the highest score for risk anticipation by predicting accidents 0.32 sec and 0.75 sec earlier compared to the best results with Adaptive Loss and dynamic parameter prediction based methods respectively.

Global Feature Aggregation for Accident Anticipation

Commercially available light field cameras have difficulty in capturing 5D (4D + time) light field videos. They can only capture still light field images or are excessively expensive for normal users to capture the light field video. To tackle this problem, we propose a deep learning-based method for synthesizing a light field video from a monocular video. We propose a new synthetic light field video dataset that renders
photorealistic scenes using Unreal Engine because no light field video dataset is available. The proposed deep learning framework synthesizes the light field video with a full set (99) of sub-aperture images from a normal monocular video. The proposed network consists of three sub-networks, namely, feature extraction, 5D light field video synthesis, and temporal consistency refinement. Experimental results show that our model can successfully synthesize the light field video for synthetic and real scenes and outperforms the previous frame-by-frame method
quantitatively and qualitatively.

5D Light Field Synthesis from a Monocular Video

As a typical cross-modal problem, visual question answering (VQA) has received increasing attention from the communities of computer vision and natural language processing. Reading and reasoning about texts in the images is a burgeoning and important topic in VQA, especially for the visually impaired assistance applications. Given a image, it aims to predict an answer to a provided natural language question closely related to its textual contents. In this paper, we propose a novel end-to-end textual content based VQA model, which grounds question answering both on the visual and textual information.

Dual Path Multi-modal High-Order Features for Textual Content based Visual Question Answering

Near-duplicate video retrieval (NDVR) is an important and challenging problem due to the increasing amount of videos uploaded to the Internet. In this paper, we propose an attention-based deep metric learning method for NDVR. Our method is based on well-established principles: We leverage two-stream networks to combine RGB and optical flow features, and incorporate an attention module to effectively deal with distractor frames commonly observed in near duplicate videos. We further aggregate the features corresponding to multiple video segments to enhance the discriminative power. The whole system is trained using a deep metric learning objective with a Siamese architecture. Our experiments show that the attention module helps eliminate redundant and noisy frames, while focusing on visually relevant frames for solving NVDR. We evaluate our approach on recent large-scale NDVR datasets, CC_WEB_VIDEO, VCDB, FIVR and SVD. To demonstrate the generalization ability of our approach, we report results in both within- and cross-dataset settings, and show that the proposed method significantly outperforms state-of-the-art approaches.

Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval

3D object reconstruction from a single-view image is a long-standing challenging problem. Previous work was difficult to accurately reconstruct 3D shapes with a complex topology which has rich details at the edges and corners. Moreover,
previous works used synthetic data to train their network, but domain adaptation problems occurred when tested on real data. In this paper, we propose a Dynamic Multi-branch Information Fusion Network (DmifNet) which can recover a high-fidelity 3D shape of arbitrary topology from a 2D image. Specifically, we design several side branches from the intermediate layers to make the network produce more diverse representations to improve the generalization ability of network. In addition, we utilize DoG (Difference of Gaussians) to extract edge geometry and corners information from input images. Then, we use a separate side branch network to process the extracted data to better capture edge geometry and corners feature information. Finally, we dynamically fuse the information of all branches to gain final predicted probability. Extensive qualitative and quantitative experiments on a large-scale publicly available dataset demonstrate the validity and efficiency of our method. Code and models are publicly available at https://github.com/leilimaster/DmifNet.

DmifNet: 3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion

Long-term visual tracking is a challenging problem.
State-of-the-art long-term trackers, e.g., GlobalTrack,
utilize region proposal networks (RPNs) to generate target
proposals. However, the performance of the trackers is
affected by occlusions and large scale or ratio variations.
To address these issues, in this paper, we are the first to
propose a novel architecture with transformers for
long-term visual tracking. Specifically, the proposed
Visual Tracking Transformer (VTT) utilizes a transformer
encoder-decoder architecture for aggregating global
information to deal with occlusion and large scale or ratio
variation. Furthermore, it also shows better discriminative
power against instance-level distractors without the need
for extra labeling and hard-sample mining. We conduct
extensive experiments on three largest long-term tracking
dataset and have achieved state-of-the-art performance.

VTT: Long-term Visual Tracking with Transformers

In recent years, there has been an increasing interest in building video summarization tools, where the goal is to automatically create a short summary of an input video that properly represents the original content. We formulate the task of video summarization as an optimization problem with a knapsack-like constraint on the total summary duration. We present ILS-SUMM, a novel video summarization algorithm to solve the subset selection problem under the knapsack constraint. Our algorithm is based on the well-known metaheuristic optimization framework - Iterated Local Search (ILS), known for its ability to avoid weak local minima and obtain a good near-global minimum. Extensive experiments show that our method finds solutions with significantly better total distance than previous methods. Moreover, to indicate the high scalability of ILS-SUMM, we introduce a new dataset consisting of videos of various lengths.

ILS-SUMM: Iterated Local Search for Unsupervised video summarization

Visual pose regression models estimate the camera pose from a query image with a single forward pass. Current models learn pose encoding from an image using deep convolutional networks which are trained per scene. The resulting encoding is typically passed to a multi-layer perceptron in order to regress the pose. In this work, we propose that scene-specific pose encoders are not required for pose regression and that encodings trained for visual similarity can be used instead. In
order to test our hypothesis, we take a shallow architecture of several fully connected layers and train it with pre-computed encodings from a generic image retrieval model. We find that these encodings are not only sufficient to regress the camera pose, but that, when provided to a branching fully connected architecture, a trained model can achieve competitive results and even surpass current state-of-the-art pose regressors in some cases. Moreover, we show that for outdoor localization, the proposed architecture is the only pose regressor, to date, consistently localizing in under 2 meters and 5 degrees.

Do We Really Need Scene-specific Pose Encoders?

Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how well the confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome and propose a learning-based approach for improving it. First, we extend two popular action recognition datasets with a reliability benchmark in form of the expected calibration error and reliability diagrams. Since our evaluation highlights that confidence values of standard action recognition architectures do not represent the uncertainty well, we introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network. The main idea of our Calibrated Action Recognition with Input Guidance (CARING) model is to learn an optimal scaling parameter depending on the video representation. We compare our model with the native action recognition networks and the temperature scaling approach - a wide spread calibration method utilized in image classification. While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.

Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models

This presentation introduces a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained from scratch for detecting objects from historical documents. We show that Doc-UFCN outperforms a state-of-the-art method on various datasets and also demonstrate that the pre-trained parts on natural scene images are not required to reach good results. In addition, we show that pre-training on multiple document datasets can improve the performances.

Premium content

NAS-EOD: an end-to-end Neural Architecture Search method for Efficient Object Detection

Downloads

Next from ICPR 2020

Global Feature Aggregation for Accident Anticipation

Similar lecture

NAS-EOD: an end-to-end Neural Architecture Search method for Efficient Object Detection