Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. 
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Many super-resolution (SR) models are optimized for high performance only and therefore lack efficiency due to large model complexity. As large models are often not practical in real-world applications, we investigate and propose novel loss functions, to enable SR with high perceptual quality from much more efficient models. The representative power for a given low-complexity generator network can only be fully leveraged by strong guidance towards the optimal set of parameters. We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. In particular, we use a Fourier space supervision loss for improved restoration of missing high-frequency (HF) content from the ground truth image and design a discriminator architecture working directly in the Fourier domain to better match the target HF distribution. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality, while at the same time retaining high restoration quality in comparison to previously proposed loss functions for this task. The performance is further improved by utilizing a combination of spatial and frequency domain losses, as both representations provide complementary information during training. On top of that, the trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.

Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Motions of organs or extremities are important features for clinical diagnosis. However, tracking and segmentation of complex, quickly changing motion patterns is challenging, certainly in the presence of occlusions. Neither state-of-the-art tracking nor motion segmentation approaches are able to deal with such cases. Thus far, motion capture systems or the like were needed which are complicated to handle and which impact on the movements. We propose a solution based on a single video camera, that is not only far less intrusive, but also a lot cheaper. The limitation of tracking and motion segmentation are overcome by a new approach to integrate prior knowledge in the form of weak labeling into motion segmentation. Using the example of Cerebral Palsy detection, we segment motion patterns of infants into the different body parts by analyzing body movements. Our experimental results show that our approach outperforms current motion segmentation and tracking approaches.

Motion Segmentation with Weak Labeling Priors

In this paper, we explore the possibility of achieving a more accurate depth estimation by fusing monocular images and Radar points using a deep neural network. We give a comprehensive study of the fusion between RGB images and Radar measurements from different aspects and proposed a working solution based on the observations. We find that the noise existing in Radar measurements is one of the main key reasons that prevents one from applying the existing fusion methods developed for LiDAR data and images to the new fusion problem between Radar data and images. The experiments are conducted on the nuScenes dataset, which is one of the first datasets which features Camera, Radar, and LiDAR recordings in diverse scenes and weather conditions. Extensive experiments demonstrate that our method outperforms existing fusion methods. We also provide detailed ablation studies to show the effectiveness of each component in our method.

Depth Estimation from Monocular Images and Sparse Radar Data

This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen real-world foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data.

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Face detection and facial points localization are interconnected tasks. Recently it has been shown that solving these two tasks jointly with a mixture of trees of parts (MTP) leads to state-of-the-art results. However, MTP, as most other methods for facial point localization proposed so far, requires a complete annotation of the training data at facial point level. This is used to predefine the structure of the trees and to place the parts correctly. In this work we extend the mixtures from trees to more general loopy graphs. In this way we can learn in a weakly supervised manner (using only the face location and orientation) a powerful deformable detector that implicitly aligns its parts to the detected face in the image. By attaching some reference points to the correct parts of our detector we can then localize the facial points. In terms of detection our method clearly outperforms the state-of-the-art, even if competing with methods that use facial point annotations during training. Additionally, without any facial point annotation at the level of individual training images, our method can localize facial points with an accuracy similar to fully supervised approaches.

/pdf/using-a-deformation-field-model-for-localizing-faces-and-3bmdyn240m.pdf

Luc Van Gool

Papers

Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Motion Segmentation with Weak Labeling Priors

Depth Estimation from Monocular Images and Sparse Radar Data

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision