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

We study the problem of robust domain adaptation in the context of unavailable target labels and source data The considered robustness is against adversarial perturbations This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data The major findings of this paper are: (i) robust source models can be transferred robustly to the target; (ii) robust domain adaptation can greatly benefit from non-robust pseudo-labels and the pair-wise contrastive loss The proposed method of using non-robust pseudo-labels performs surprisingly well on both clean and adversarial samples, for the task of image classification We show a consistent performance improvement of over $10\%$ in accuracy against the tested baselines on four benchmark datasets

Unsupervised Robust Domain Adaptation without Source Data.

Fashion is a major segment in e-commerce with growing importance and a steadily increasing number of products. Since manual annotation of apparel items is very tedious, the product databases need to be organized automatically, e.g. by image classification. Common image classification approaches are based on features engineered for general purposes which perform poorly on specific images of apparel. We therefore propose to learn discriminative features based on a small set of annotated images. We experimentally evaluate our method on a dataset with 30,000 images containing apparel items, and compare it to other engineered and learned sets of features. The classification accuracy of our features is significantly superior to designed HOG and SIFT features (43.7% and 16.1% relative improvement, respectively). Our method allows for fast feature extraction and training, is easy to implement and, unlike deep convolutional networks, does not require powerful dedicated hardware.

/pdf/discriminative-learning-of-apparel-features-3pz1o5fj35.pdf

Discriminative learning of apparel features

Although more and more computer-aided technologies are utilised or demonstrated on well-known monuments or archaeological sites, there is at least for the professionals working in the field still some lack of clarity about their application. The main idea of our research project is to construct a prototype of a tool that tries to bring new technologies closer to the daily practice. It incorporates recent developments in computer vision and reverse engineering, while at the same time tries to answer the practical concerns from civil servants, architects, topographers, art-historians... who are responsible for the conservation of monuments or archaeological sites. The proposed system covers automatic correspondence analysis and point cloud manipulation to build up a textured 3D model. This model then acts as the central core of a multimedia data structure for the annotation, geometric and thematic interrogation and visualisation of the building or site being studied.

/pdf/from-a-conservationist-s-point-of-view-11yv45kiid.pdf

From a conservationist's point of view

Modeling of three-dimensional (3D) objects from image sequences is a challenging problem and has been a research topic for many years. Important theoretical and algorithmic results were achieved that allow to extract even complex 3D models of scenes from sequences of images. One recent effort has been to reduce the amount of calibration and to avoid restrictions on the camera motion. In this contribution an approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.

Luc Van Gool

Papers

Unsupervised Robust Domain Adaptation without Source Data.

Discriminative learning of apparel features

From a conservationist's point of view

to appear proceedings SPIE Electronic Imaging 2000, Three-Dimensional Image Capture and Applications III

Editorial: Special issue on 3D representation for object and scene recognition