ECCV 2018 Papers

The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them into one vector to represent the set, and then compute the cosine similarity between sets. Instead, we design a neural network architecture that can directly learn set-wise verification. Our contributions are: (i) We propose a Deep Comparator Network (DCN) that can ingest a pair of sets (each may contain a variable number of images) as inputs, and compute a similarity between the pair -- this involves attending to multiple discriminative local regions (landmarks), and comparing local descriptors between pairs of faces; (ii) To encourage high-quality representations for each set, internal competition is introduced for recalibration based on the landmark score; (iii) Inspired by image retrieval, a novel hard sample mining regime is proposed to control the sampling process, such that the DCN is complementary to the standard classification models. Evaluations on the IARPA Janus face recognition benchmarks show that the comparator networks outperform the previous state-of-the-art results by a large margin.

We present a new combined approach for monocular model-based 3D tracking. A preliminary object pose is estimated by using a keypoint-based technique. The pose is then refined by optimizing the contour energy function. The energy determines the degree of correspondence between the contour of the model projection and the image edges. It is calculated based on both the intensity and orientation of the raw image gradient. For optimization, we propose a technique and search area constraints that allow overcoming the local optima and taking into account information obtained through keypoint-based pose estimation. Owing to its combined nature, our method eliminates numerous issues of keypoint-based and edge-based approaches. We demonstrate the efficiency of our method by comparing it with state-of-the-art methods on a public benchmark dataset that includes videos with various lighting conditions, movement patterns, and speed.

This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. In contrast to existing approaches, our model can understand rich text, whether it is a single word, a phrase, or a sentence, and generate multiple possible palettes from it. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT). Our proposed model called Text2Colors consists of two conditional generative adversarial networks: the text-to-palette generation networks and the palette-based colorization networks. The former captures the semantics of the text input and produce relevant color palettes. The latter colorizes a grayscale image using the generated color palette. Our evaluation results show that people preferred our generated palettes over ground truth palettes and that our model can effectively reflect the given palette when colorizing an image.

In this paper, we propose a collaborative deep reinforcement learning (C-DRL) method for multi-object tracking. Most existing multi-object tracking methods employ the tracking-by-detection strategy which first detects objects in each frame and then associates them across different frames. However, the performance of these methods rely heavily on the detection results, which are usually unsatisfied in many real applications, especially in crowded scenes. To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unified network via deep reinforcement learning. Specifically, we consider each object as an agent and track it via the prediction network, and seek the optimal tracked results by exploiting the collaborative interactions of different agents and environments via the decision network, so that the influences of occlusions and noisy detection results can be well alleviated. Experimental results on the challenging MOT15 and MOT16 benchmarks are presented to show the efficiency of our approach.

We introduce coded two-bucket (C2B) imaging, a new operating principle for computational sensors with applications in active 3D shape estimation and coded-exposure imaging. A C2B sensor modulates the light arriving at each pixel by controlling which of the pixel's two "buckets" should integrate it. C2B sensors output two images per video frame---one per bucket---and allow rapid, fully-programmable, per-pixel control of the active bucket. Using these properties as a starting point, we (1) develop an image formation model for these sensors, (2) couple them with programmable light sources to acquire illumination mosaics, i.e., images of a scene under many different illumination conditions whose pixels have been multiplexed onto the sensor plane and acquired in one shot, and (3) show how to process illumination mosaics to acquire time-varying depth or normal maps of dynamic scenes at the sensor's native resolution. We present the first experimental demonstration of these capabilities, using a fully functional C2B camera prototype. Key to this prototype is a C2B sensor that was designed by us, fabricated in a standard CMOS imaging technology, and demonstrated for the first time in this paper.

The quick detection of specific substances in objects such as produce items via non-destructive visual cues is vital to ensuring the quality and safety of consumer products. At the same time, it is well-known that the fluorescence excitation-emission characteristics of many organic objects can serve as a kind of ``fingerprint'' for detecting the presence of specific substances in classification tasks such as determining if something is safe to consume. However, conventional capture of the fluorescence excitation-emission matrix can take on the order of minutes and can only be done for point measurements. In this paper, we propose a coded illumination approach whereby light spectra are learned such that key visual fluorescent features can be easily seen for material classification. We show that under a single coded illuminant, we can capture one RGB image and perform pixel-level classifications of materials at high accuracy. This is demonstrated through effective classification of different types of honey and alcohol using real images.

In this paper, we propose a novel method to compress CNNs by reconstructing the network from a small set of spatial convolution kernels. Starting from a pre-trained model, we extract representative 2D kernel centroids using k-means clustering. Each centroid replaces the corresponding kernels of the same cluster, and we use indexed representations instead of saving whole kernels. Kernels in the same cluster share their weights, and we fine-tune the model while keeping the compressed state. Furthermore, we also suggest an efficient way of removing redundant calculations in the compressed convolutional layers. We experimentally show that our technique works well without harming the accuracy of widely-used CNNs. Also, our ResNet-18 even outperforms its uncompressed counterpart at ILSVRC2012 classification task with over 10x compression ratio.

Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects – forming a “dictionary” of concepts acquired through the learning process. In this work we introduce a simple, efficient zero-shot learning approach based on this observation. Our approach, which we call Neuron Importance-Aware Weight Transfer (NIWT), learns to map domain knowledge about novel “unseen” classes onto this dictionary of learned concepts and then optimizes for network parameters that can effectively combine these concepts – essentially learning classifiers by discovering and composing learned semantic concepts in deep networks. Our approach shows improvements over previous approaches on the CUBirds and AWA2 generalized zero-shot learning benchmarks. We demonstrate our approach on a diverse set of semantic inputs as external domain knowledge including attributes and natural language captions. Moreover by learning inverse mappings, NIWT can provide visual and textual explanations for the predictions made by the newly learned classifiers and provide neuron names. Our code is available at https://github.com/ramprs/neuron-importance-zsl.

Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are mainly studied in classification, special properties may be inherited for those targeting on segmentation models which require additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in segmentation. We observe that spatial consistency information can be potentially leveraged to recognize/detect adversarial examples robustly even when facing adaptive attacker who has access to the model and detection strategies. We also show that adversarial examples based on attacks we considered barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.

Temporal action proposal generation is an important task, akin to object proposals, temporal action proposals are intended to capture "clips" or temporal intervals in videos that are likely to contain an action. Previous methods can be divided to two groups: sliding window ranking and actionness score grouping. Sliding windows uniformly cover all segments in videos, but the temporal boundaries are imprecise; grouping based method may have more precise boundaries but it may omit some proposals when the quality of actionness score is low. Based on the complementary characteristics of these two methods, we propose a novel Complementary Temporal Action Proposal (CTAP) generator. Specifically, we apply a Proposal-level Actionness Trustworthiness Estimator (PATE) on the sliding windows proposals to generate the probabilities indicating whether the actions can be correctly detected by actionness scores, the windows with high scores are collected. The collected sliding windows and actionness proposals are then processed by a temporal convolutional neural network for proposal ranking and boundary adjustment. CTAP outperforms state-of-the-art methods on average recall (AR) by a large margin on THUMOS-14 and ActivityNet 1.3 datasets. We further apply CTAP as a proposal generation method in an existing action detector, and show consistent significant improvements.

Image geolocalization is the task of identifying the location depicted in a photo based only on its visual information. This task is inherently challenging since many photos have only few, possibly ambiguous cues to their geolocation. Recent work has cast this task as a classification problem by partitioning the earth into a set of discrete cells that correspond to geographic regions. The granularity of this partitioning presents a critical trade-off; using fewer but larger cells results in lower location accuracy while using more but smaller cells reduces the number of training examples per class and increases model size, making the model prone to overfitting. To tackle this issue, we propose a simple but effective algorithm, combinatorial partitioning, which generates a large number of fine-grained output classes by intersecting multiple coarse-grained partitionings of the earth. Each classifier votes for the fine-grained classes that overlap with their respective coarse-grained ones. This technique allows us to predict locations at a fine scale while maintaining sufficient training examples per class. Our algorithm achieves the state-of-the-art performance in location recognition on multiple benchmark datasets.

Most conventional photometric stereo algorithms inversely solve a BRDF-based image formation model. However, the actual imaging process is often far more complex due to the global light transport on the non-convex surfaces. This paper presents a photometric stereo network that directly learns relationships between the photometric stereo input and surface normals of a scene. For handling unordered, arbitrary number of input images, we merge all the input data to the intermediate representation called {it observation map} that has a fixed shape, is able to be fed into a CNN. To improve both training and prediction phases, we take into account the rotational pseudo-invariance of the observation map that is derived from the isotropic constraint. For training the network, we create a synthetic photometric stereo dataset that is generated by a physics-based renderer, therefore the global light transport is considered. Our experimental results on both synthetic and real datasets show that our method outperforms conventional BRDF-based photometric stereo algorithms especially when scenes are highly non-convex.

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the pre-processing perception system while the supervised learning-based models are limited by the accessibility of extensive human experience. We present a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator. To alleviate the low exploration efficiency for large continuous action space that often prohibits the use of classical RL on challenging real tasks, our CIRL explores over a reasonably constrained action space guided by encoded experiences that imitate human demonstrations, building upon Deep Deterministic Policy Gradient (DDPG). Moreover, we propose to specialize adaptive policies and steering-angle reward designs for different control signals (i.e. follow, straight, turn right, turn left) based on the shared representations to improve the model capability in tackling with diverse cases. Extensive experiments on CARLA driving benchmark demonstrate that CIRL substantially outperforms all previous methods in terms of the percentage of successfully completed episodes on a variety of goal-directed driving tasks. We also show its superior generalization capability in unseen environments. To our knowledge, this is the first successful case of the learned driving policy by reinforcement learning in the high-fidelity simulator, which performs better than supervised imitation learning.

Intrinsic image decomposition is a long-standing, highly challenging computer vision problem, where ground truth data is very difficult to acquire. We explore the idea of using synthetic data to train CNN-based intrinsic image decomposition models, and applying these learned models to real-world images. To that end, we present CGINTRINSICS, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions. The image generation process we use is carefully designed to yield high-quality, realistic images, which we find to be critical for this problem. We also propose a new end-to-end learning method that learns better decompositions by leveraging CGINTRINSICS , and optionally IIW and SAW, two recent datasets of sparse annotations on real-world images. Surprisingly, we find that a decomposition network trained solely on our synthetic data outperforms the state-of-the-art on both IIW and SAW, and performance improves even further when IIW and SAW data is added during training. Our work demonstrates the unreasonable effectiveness of carefully-rendered synthetic data for the intrinsic images task.

We propose Convolutional Block Attention Module (CBAM), a simple and effective attention module that can be integrated with any feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architecture seamlessly with negligible overheads. Our module is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS COCO detection, and VOC 2007 detection datasets. Our experiments show consistent improvements on classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available upon the acceptance of the paper.

We present an interpretable framework for path prediction that leverages dependencies between agents' behaviors and their spatial navigation environment. We exploit two sources of information: the past motion trajectory of the agent of interest and a wide top-view image of the navigation scene. We propose a Clairvoyant Attentive Recurrent Network (CAR-Net) that learns where to look in a large image of the scene when solving the path prediction task. Our method can attend to any area, or a combination of areas, within the raw image (e.g., road intersections) when predicting the trajectory of the agent. This allows us to visualize fine-grained semantic elements of navigation scenes that influence the prediction of trajectories. To study the impact of space on agents' trajectories, we build a new dataset made of top-view images of hundreds of scenes (Formula One racing tracks) where agents' behaviors are heavily influenced by known areas in the images (e.g., upcoming turns). CAR-Net successfully attends to these salient regions. Additionally, CAR-Net reaches state-of-the-art accuracy on the standard trajectory forecasting benchmark, Stanford Drone Dataset (SDD). Finally, we show CAR-Net's ability to generalize to unseen scenes.

We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL). C-WSL uses a simple count-based region selection algorithm to select high-quality regions, each of which covers a single object instance during training, and improves existing WSL methods by training with the selected regions. To demonstrate the effectiveness of C-WSL, we integrate it into two WSL architectures and conduct extensive experiments on VOC2007 and VOC2012. Experimental results show that C-WSL leads to large improvements in WSL and that the proposed approach significantly outperforms the state-of-the-art methods. The results of annotation experiments on VOC2007 suggest that a modest extra time is needed to obtain per-class object counts compared to labeling only object categories in an image. Furthermore, we reduce the annotation time by more than 2 times and 38 times compared to center-click and bounding-box annotations.

We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet. Unlike previous eorts, BusterNet is a pure, end-to-end trainable, deep neural network solution. It features a two-branch architecture followed by a fu- sion module. The two branches localize potential manipulation regions (by looking for visual artifacts) and copy-move regions (by assessing vi- sual similarities), respectively. To the best of our knowledge, this is the rst CMFD algorithm with discernibility to localize source/target re- gions.We also propose simple schemes for synthesizing large-scale CMFD samples using out-of-domain datasets, and stage-wise strategies for eec- tive BusterNet training. Our extensive studies demonstrate that Buster- Net outperforms state-of-the-art copy-move detection algorithms by a large margin on the two publicly available datasets, CASIA and CoMo- FoD, and that it is robust against various known attacks.

We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image. Our novel convolutional architecture has a simultaneous view of all frames in the burst, and by construction treats them in an order-independent manner. This enables it to effectively detect and leverage subtle cues scattered across different frames, while ensuring that each frame gets a full and equal consideration regardless of its position in the sequence. We train the network with richly varied synthetic data consisting of camera shake, realistic noise, and other common imaging defects. The method demonstrates consistent state of the art burst image restoration performance for highly degraded sequences of real-world images, and extracts accurate detail that is not discernible from any of the individual frames in isolation.