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

/pdf/domain-adaptive-semantic-segmentation-with-self-supervised-3olaxljndc.pdf

Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our novel path supervision the annotator loosely follows the object with the cursor while watching the video, providing a path annotation for each object in the sequence. Our approach is able to turn such weak annotations into dense box trajectories. Our experiments on existing datasets prove that our framework produces more accurate annotations than the state of the art, in a fraction of the time. We further validate our approach by crowdsourcing the PathTrack dataset, with more than 15,000 person trajectories in 720 sequences. Tracking approaches can benefit training on such large-scale datasets, as did object recognition. We prove this by re-training an off-the-shelf person matching network, originally trained on the MOT15 dataset, almost halving the misclassification rate. Additionally, training on our data consistently improves tracking results, both on our dataset and on MOT15. On the latter, we improve the top-performing tracker (NOMT) dropping the number of IDSwitches by 18% and fragments by 5%.

PathTrack: Fast Trajectory Annotation with Path Supervision

This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval. Unlike previous methods, which develop or learn sophisticated regularizers for classifiers, our method learns a new image representation by exploiting the distribution patterns of all available data for the task at hand. Particularly, a rich set of visual prototypes are sampled from all available data, and are taken as surrogate classes to train discriminative classifiers; images are projected via the classifiers; the projected values, similarities to the prototypes, are stacked to build the new feature vector. The training set is noisy. Hence, in the spirit of ensemble learning we create a set of such training sets which are all diverse, leading to diverse classifiers. The method is dubbed Ensemble Projection (EP). EP captures not only the characteristics of individual images, but also the relationships among images. It is conceptually simple and computationally efficient, yet effective and flexible. Experiments on eight standard datasets show that: (1) EP outperforms previous methods for semi-supervised image classification; (2) EP produces promising results for self-taught image classification, where unlabeled samples are a random collection of images rather than being from the same distribution as the labeled ones; and (3) EP improves over the original features for image clustering. The code of the method is available on the project page.

/pdf/unsupervised-high-level-feature-learning-by-ensemble-452tu254wr.pdf

Unsupervised high-level feature learning by ensemble projection for semi-supervised image classification and image clustering

This paper presents a service that creates complete and realistic 3D models out of a set of photographs taken with a consumer camera. In contrast to other systems which produce sparse point clouds or individual depth maps, our system automatically generates textured and dense models that require little or no post-processing. Our reconstruction pipeline features automatic camera parameter retrieval from the web and intelligent view selection. This ARC3D system is available as a public, free-to-use web service (http://www.arc3d.be). Results are made available both as a full-resolution model and as a low-resolution for web browser viewing using WebGL.

A public system for image based 3D model generation

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal centers of objects are click-annotated in bird’s view scenes. Stage-2 learns to refine the cylindrical proposals to get cuboids and confidence scores, using a few well-labeled instances. Using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves \(85\) \(-\) \(95\)% the performance of current top-leading, fully supervised detectors (requiring 3, 712 exhaustively and precisely annotated scenes with 15, 654 instances). Moreover, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, supporting both automatic and active (human-in-the-loop) working modes. The annotations generated by our model can be used to train 3D object detectors, achieving over 94% of their original performance (with manually labeled training data). Our experiments also show our model’s potential in boosting performance when given more training data. Above designs make our approach highly practical and introduce new opportunities for learning 3D object detection at reduced annotation cost.

Luc Van Gool

Papers

Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

PathTrack: Fast Trajectory Annotation with Path Supervision

Unsupervised high-level feature learning by ensemble projection for semi-supervised image classification and image clustering

A public system for image based 3D model generation

Weakly Supervised 3D Object Detection from Lidar Point Cloud