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/branched-multi-task-networks-deciding-what-layers-to-share-2x7nwkaefi.pdf

Branched Multi-Task Networks: Deciding What Layers To Share

This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement. The key idea is to decompose the photo enhancement process into hierarchically multiple sub-problems, which can be better conquered from bottom to up. On the top level, we propose a perception-based division to learn additive and multiplicative components, required to translate a low-quality image or video into its high-quality counterpart. On the intermediate level, we use a frequency-based division with generative adversarial network (GAN) to weakly supervise the photo enhancement process. On the lower level, we design a dimension-based division that enables the GAN model to better approximates the distribution distance on multiple independent one-dimensional data to train the GAN model. While considering all three hierarchies, we develop multiscale and recurrent training approaches to optimize the image and video enhancement process in a weakly-supervised manner. Both quantitative and qualitative results clearly demonstrate that the proposed DACAL achieves the state-of-the-art performance for high-resolution image and video enhancement.

Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement.

Existing learning methods for LiDAR-based applications use 3D points scanned under a pre-determined beam configuration, e.g., the elevation angles of beams are often evenly distributed. Those fixed configurations are task-agnostic, so simply using them can lead to sub-optimal performance. In this work, we take a new route to learn to optimize the LiDAR beam configuration for a given application. Specifically, we propose a reinforcement learning-based learning-to-optimize (RL-L2O) framework to automatically optimize the beam configuration in an end-to-end manner for different LiDAR-based applications. The optimization is guided by the final performance of the target task and thus our method can be integrated easily with any LiDAR-based application as a simple drop-in module. The method is especially useful when a low-resolution (low-cost) LiDAR is needed, for instance, for system deployment at a massive scale. We use our method to search for the beam configuration of a low-resolution LiDAR for two important tasks: 3D object detection and localization. Experiments show that the proposed RL-L2O method improves the performance in both tasks significantly compared to the baseline methods. We believe that a combination of our method with the recent advances of programmable LiDARs can start a new research direction for LiDAR-based active perception.

End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization

Multimodal question answering in the cultural heritage domain allows visitors to ask questions in a more natural way and thus provides better user experiences with cultural objects while visiting a museum, landmark or any other historical site. In this paper, we introduce the construction of a golden standard dataset that will aid research of multimodal question answering in the cultural heritage domain. The dataset, which will be soon released to the public, contains multimodal content including images of typical artworks from the fascinating old-Egyptian Amarna period, related image-containing documents of the artworks and over 800 multimodal queries integrating visual and textual questions. The multimodal questions and related documents are all in English. The multimodal questions are linked to relevant paragraphs in the related documents that contain the answer to the multimodal query.

A dataset for multimodal question answering in the cultural heritage domain

Humans can communicate emotions through a plethora of facial expressions, each with its own intensity, nuances and ambiguities. The generation of such variety by means of conditional GANs is limited to the expressions encoded in the used label system. These limitations are caused either due to burdensome labelling demand or the confounded label space. On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability. In this paper, we propose a novel GAN-based framework that learns an expressive and interpretable conditional space (usable as a label space) of emotions, instead of conditioning on handcrafted labels. Our framework only uses the categorical labels of basic emotions to learn jointly the conditional space as well as emotion manipulation. Such learning can benefit from the image variability within discrete labels, especially when the intrinsic labels reside beyond the discrete space of the defined. Our experiments demonstrate the effectiveness of the proposed framework, by allowing us to control and generate a gamut of complex and compound emotions while using only the basic categorical emotion labels during training. Our source code is available at https://github.com/stefanodapolito/GANmut.

/pdf/ganmut-learning-interpretable-conditional-space-for-gamut-of-zz2stwu0qb.pdf

Luc Van Gool

Papers

Branched Multi-Task Networks: Deciding What Layers To Share

Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement.

End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization

A dataset for multimodal question answering in the cultural heritage domain

GANmut: Learning Interpretable Conditional Space for Gamut of Emotions