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

Data annotation is the most labor-intensive part for the acquisition of a multimodal corpus. 3D vision technology can ease the annotation process, especially when continuous surface deformations need to be extracted accurately and consistently over time. In this paper, we give an example use of such technology, namely the acquisition of an audio-visual corpus comprising detailed dynamic face geometry, transcription of the corpus text into the phonological representation, accurate phone segmentation, fundamental frequency extraction, and signal intensity estimation of the speech signals. By means of the example, we will discuss the advantages and challenges of integrating non-invasive 3D vision capture techniques into a setup for recording multimodal data.

3D Vision Technology for Capturing Multimodal Corpora: Chances and Challenges

. In this paper, we study a practical space-time video super-resolution (STVSR) problem which aims at generating a high-framerate high-resolution sharp video from a low-framerate low-resolution blurry video. Such problem often occurs when recording a fast dynamic event with a low-framerate and low-resolution camera, and the captured video would suffer from three typical issues: i) motion blur occurs due to ob-ject/camera motions during exposure time; ii) motion aliasing is un-avoidable when the event temporal frequency exceeds the Nyquist limit of temporal sampling; iii) high-frequency details are lost because of the low spatial sampling rate. These issues can be alleviated by a cascade of three separate sub-tasks, including video deblurring, frame interpolation, and super-resolution, which, however, would fail to capture the spatial and temporal correlations among video sequences. To address this, we propose an interpretable STVSR framework by leveraging both model-based and learning-based methods. Specifically, we formulate STVSR as a joint video deblurring, frame interpolation, and super-resolution problem, and solve it as two sub-problems in an alternate way. For the first sub-problem, we derive an interpretable analytical solution and use it as a Fourier data transform layer. Then, we propose a recurrent video enhancement layer for the second sub-problem to further recover high-frequency details. Extensive experiments demonstrate the superiority of our method in terms of quantitative metrics and visual quality.

Towards Interpretable Video Super-Resolution via Alternating Optimization

Most state-of-the-art object retrieval systems rely on ad-hoc similarities between histograms of quantised local descriptors to find, in their databases, all the images relevant to an image query. In this work, our goal is to replace those similarities with ones that are specifically trained to maximize the retrieval accuracy. We propose to use a simple and very general linear model whose weights directly represent the similarity values. We devise a variant of rank-SVM to learn those weights automatically from training data with fast convergence and we propose techniques to limit the number of parameters of the model and prevent overfitting. Importantly, the flexibility of our model allows us to seamlessly incorporate well-known image retrieval schemes such as burstiness, negative evidence and idf weighting, and still exploit inverted files for efficiency in the large-scale setting. In our experiments, we show that our approach consistently and significantly outperforms the similarities used in several state-of-the-art systems on 4 standard benchmark datasets. In particular, on the Oxford105k dataset, our method outperforms the closest competitor by 6%.

/pdf/learning-to-rank-bag-of-word-histograms-for-large-scale-3dww5t6q7s.pdf

Learning to rank bag-of-word histograms for large-scale object retrieval

Visual tracking is the task of estimating the trajectory of an object in a video given its initial location. This is usually done by combining at each step an appearance and a motion model. In this work, we learn from a small set of training trajectory annotations how the objects in the scene typically move. We learn the relative weight between the appearance and the motion model. We call this weight: visual deceptiveness. At test time, we transfer the deceptiveness and the displacement from the closest trajectory annotation to infer the next location of the object. Further, we condition the transference on an event model. On a set of 161 manually annotated test trajectories, we show in our experiments that learning from just 10 trajectory annotations halves the center location error and improves the success rate by about 10%.

/pdf/appearances-can-be-deceiving-learning-visual-tracking-from-47j28btsj0.pdf

Luc Van Gool

Papers

3D Vision Technology for Capturing Multimodal Corpora: Chances and Challenges

Towards Interpretable Video Super-Resolution via Alternating Optimization

Learning to rank bag-of-word histograms for large-scale object retrieval

Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations

Advanced remote sensing information system at ETH Zürich and DLR