Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be contrasted with other instances, called negatives, that are considered as noise. However, several instances in a dataset are drawn from the same distribution and share underlying semantic information. A good data representation should contain relations, or semantic similarity, between the instances. Contrastive learning implicitly learns relations but considering all negatives as noise harms the quality of the learned relations. To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE). Our training objective is a soft contrastive learning one. Instead of hard classifying positives and negatives, we estimate from one view of a batch a continuous distribution to push or pull instances based on their semantic similarities. This target similarity distribution is sharpened to eliminate noisy relations. The model predicts for each instance, from another view, the target distribution while contrasting its positive with negatives. Experimental results show that SCE is Top-1 on the ImageNet linear evaluation protocol at 100 pretraining epochs with 72.1% accuracy and is competitive with state-of-the-art algorithms by reaching 75.4% for 200 epochs with multi-crop. We also show that SCE is able to generalize to several tasks. Source code is available here: https://github.com/CEA-LIST/SCE.

Abstract Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be contrasted with other instances, called negatives, that are considered as noise. However, several instances in a dataset are drawn from the same distribution and share underlying semantic information. A good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise. To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE). Our training objective is a soft contrastive one that brings the positives closer and estimates a continuous distribution to push or pull negative instances based on their learned similarities. We validate empirically our approach on both image and video representation learning. We show that SCE performs competitively with the state of the art on the ImageNet linear evaluation protocol for fewer pretraining epochs and that it generalizes to several downstream image tasks. We also show that SCE reaches state-of-the-art results for pretraining video representation and that the learned representation can generalize to video downstream tasks. Source code is available here: https://github.com/juliendenize/eztorch .

To overcome the limitations of the so-called Industry 4.0 focusing on mass production and full automation, a novel paradigm was recently introduced, namely Industry 5.0, which aims at an increased collaboration between humans and machines, and particularly robots, instead of replacing the former with the latter. This challenge requires novel interactive intelligent robots able to perform complex tasks easily and efficiently and to collaborate on the fly with humans whenever required, be it for training or working. In this work, the Robot Companion, a novel demonstrator of this paradigm, is introduced. It combines robotics, Artificial Intelligence, software engineering and embedded systems technologies, and targets industrial assembly tasks. First tests show that this robot can efficiently assemble a representative gear system autonomously or in collaboration with human operators.

In recent years, we have witnessed increasingly high performance in the field of autonomous end-to-end driving. In particular, more and more research is being done on driving in urban environments, where the car has to follow high level commands to navigate. However, few evaluations are made on the ability of these agents to react in an unexpected situation. Specifically, no evaluations are conducted on the robustness of driving agents in the event of a bad high-level command. We propose here an evaluation method, namely a benchmark that allows to assess the robustness of an agent, and to appreciate its understanding of the environment through its ability to keep a safe behavior, regardless of the instruction.

In this paper, we propose a self-supervised method for video representation learning based on Contrastive Predictive Coding (CPC) [27]. Previously, CPC has been used to learn representations for different signals (audio, text or image). It benefits from the use of an autoregressive modeling and contrastive estimation to learn long-term relations inside raw signal while remaining robust to local noise. Our self-supervised task consists in predicting the latent representation of future segments of the video. As opposed to generative models, predicting directly in the feature space is easier and avoid incertitude problems for long-term predictions. Today, using CPC to learn representations for videos remains challenging due to the structure and the high dimensionality of the signal. We demonstrate experimentally that the representations learned by the network are useful for action recognition. We test it with different input types such as optical flows, image differences and raw images on different datasets (UCF-101 and HMDB51). It gives consistent results across the modalities. At last, we notice the utility of our pre-training method by achieving competitive results for action recognition using few labeled data.

In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly computes detection and feature extraction steps through a single deep Convolutional Neural Network architecture. Sharing feature maps between the two tasks for jointly describing people commonalities and specificities allows faster runtime, which is valuable in real-world applications. In addition to reaching state-of-the-art accuracy, this multi-task model can be sequentially trained task-by-task, which results in a broader acceptance of input dataset types. Indeed, we show that aggregating more pedestrian detection datasets without costly identity annotations makes the shared feature maps more generic, and improves re-ID precision. Moreover, these boosted shared feature maps result in re-ID features more robust to a cross-dataset scenario.

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization, visibility characterization and 3D dimension estimation. Its architecture is based on a new coarse-to-fine object proposal that boosts the vehicle detection. Moreover, the Deep MANTA network is able to localize vehicle parts even if these parts are not visible. In the inference, the networks outputs are used by a real time robust pose estimation algorithm for fine orientation estimation and 3D vehicle localization. We show in experiments that our method outperforms monocular state-of-the-art approaches on vehicle detection, orientation and 3D location tasks on the very challenging KITTI benchmark.

Given an untextured 3D car models dataset, are we able to learn a robust make and model classifier which will be applied on real color images? One solution consists in finding a common representation between synthetic edge images and real color images. To address this issue, we introduce novel edge-color invariant features for 2D/3D car fine-grained classification. These features are learned simultaneously on real color and edge images of cars using a deep architecture. Using these accurate features, we propose to learn on edges synthetic images a fine-grained classifier which will be afterwards applied to real color images. The 3D car models dataset allows to automatically generate multi-views synthetic images using non-photorealistic edge rendering. Experimentally, we show efficiency of our learned edge-color invariant features for make and model recognition.

We propose a new approach for accurate car pose estimation in images using only a dataset of 3D untextured models. Our algorithm detects both a car and its 3D pose. It is based on the matching of 3D models with the car in the image. With a part detector based on Convolutional Neural Networks, interest points corresponding to predefined 3D parts are extracted from the image. Then, we use the car geometry to find which parts are relevant across viewpoints. Finally, a 2D/3D pose estimator is used to recover the 3D pose of the car. The main contribution is to learn appearance and geometry models from 3D models dataset only. Experiments show that the method is very competitive for car detection and coarse viewpoint classification and improves the 3D pose estimation over the state-of-the-art methods.

Building large video datasets is a crucial task for many applications but is also very expensive in practice. In order to avoid annotating all the frames, the annotations from the labeled frames can be propagated using an offline tracker for each object. Following methods based on dynamic programming and eventually distance transforms, we introduce a new penalization which favors some given displacements between two frames without increasing the complexity of the optimization. In order to speed up this step we also propose to use an exact coarse to fine process. Experimental results show that the proposed energy performs better than previous ones and that our exact coarse to fine optimization leads to a significant speed-up in some scenarios.

The success of kernel methods including support vector networks (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and bioinformatics. We focus in this paper on object recognition using a new type of kernel referred to as ldquocontext-dependentrdquo. Objects, seen as constellations of local features (interest points, regions, etc.), are matched by minimizing an energy function mixing (1) a fidelity term which measures the quality of feature matching, (2) a neighborhood criteria which captures the object geometry and (3) a regularization term. We will show that the fixed-point of this energy is a ldquocontext-dependentrdquo kernel (ldquoCDKrdquo) which also satisfies the Mercer condition. Experiments conducted on object recognition show that when plugging our kernel in SVMs, we clearly outperform SVMs with ldquocontext-freerdquo kernels.

The success of kernel methods including support vector machines (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and bioinformatics.