ECCV 2020 Papers

Domain Adaptation as an important tool aims to explore a generalized model trained on well-annotated source knowledge to address learning issue on target domain with insufficient or even no annotation. Current approaches typically incorporate data from source and target domains for training stage to deal with domain shift. However, most domain adaptation tasks generally suffer from the problem that measuring the domain shift tends to be impossible when target data is inaccessible. In this paper, we propose a novel algorithm, Hybrid Generative Network (HGNet) for Zero-shot Domain Adaptation, which embeds an adaptive feature separation (AFS) module into generative architecture. Specifically, AFS module can adaptively distinguish classification-relevant features from classification-irrelevant ones to learn domain-invariant and discriminative representations when task-relevant target instances are invisible. To learn high-quality feature representation, we also develop hybrid generative strategy to ensure the uniqueness of feature separation and completeness of semantic information. Extensive experimental results on several benchmarks illustrate that our method achieves more promising results than state-of-the-art approaches."

Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Depth Estimation Network (HDNet), an end-to-end framework for absolute root joint localization in the camera coordinate space. Our HDNet first estimates the 2D human pose with heatmaps of the joints. These estimated heatmaps serve as attention masks for pooling features from image regions corresponding to the target person. A skeleton-based Graph Neural Network (GNN) is utilized to propagate features among joints. We formulate the target depth regression as a bin index estimation problem, which can be transformed with a soft-argmax operation from the classification output of our HDNet. We evaluate our HDNet on the root joint localization and root-relative 3D pose estimation tasks with two benchmark datasets, i.e., Human3.6M and MuPoTS-3D. The experimental results show that we outperform the previous state-of-the-art consistently under multiple evaluation metrics. Our source code is available at: https://github.com/jiahaoLjh/HumanDepth ."

Predicting the class label from the partially observed activity sequence is a very hard task, as the observed early segments of different activities can be very similar. In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated. Specifically, a Hard Instance-Interference Class (HI-IC) bank is designed, which dynamically records the hard similar pairs. Based on the HI-IC bank, a novel adversarial learning scheme is proposed to train our HARD-Net, which thus grants our network with the strong capability in mining subtle discrimination information for 3D early activity prediction. We evaluate our proposed HARD-Net on two public activity datasets and achieve state-of-the-art performance."

There has been an explosive demand for bringing machine learning (ML) powered intelligence into numerous Internet-of-Things (IoT) devices. However, the effectiveness of such intelligent functionality requires in-situ continuous model adaptation for adapting to new data and environments, while the on-device computing and energy resources are usually extremely constrained. Neither traditional hand-crafted (e.g., SGD, Adagrad, and Adam) nor existing meta optimizers are specifically designed to meet those challenges, as the former requires tedious hyper-parameter tuning while the latter are often costly due to the meta algorithms’ own overhead. To this end, we propose hardware-aware learning to optimize (HALO), a practical meta optimizer dedicated to resource-efficient on-device adaptation. Our HALO optimizer features the following highlights: (1) faster adaptation speed (i.e., taking fewer data or iterations to reach a specified accuracy) by introducing a new regularizer to promote empirical generalization; and (2) lower per-iteration complexity, thanks to a stochastic structural sparsity regularizer being enforced. Furthermore, the optimizer itself is designed as a very light-weight RNN and thus incurs negligible overhead. Ablation studies and experiments on five datasets, six optimizees, and two state-of-the-art (SOTA) edge AI devices validate that, while always achieving a better accuracy (↑0.46% - ↑20.28%), HALO can greatly trim down the energy cost (up to ↓60%) in adaptation, quantified using an IoT device or SOTA simulator. Codes and pre-trained models are at https://github.com/RICE-EIC/HALO ."

We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical idea of H3DNet is to predict a hybrid set of geometric primitives, i.e., BB centers, BB face centers, and BB edge centers. We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives. This distance function enables continuous optimization of object proposals, and its local minimums provide high-fidelity object proposals. H3DNet then utilizes a matching and refinement module to classify object proposals into detected objects and fine-tune the geometric parameters of the detected objects. The hybrid set of geometric primitives not only provides more accurate signals for object detection than using a single type of geometric primitives, but it also provides an overcomplete set of constraints on the resulting 3D layout. Therefore, H3DNet can tolerate outliers in predicted geometric primitives. Our model achieves state-of-the-art 3D detection results on two large datasets with real 3D scans, ScanNet and SUN RGB-D."

Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV). Experiments on two popular indoor datasets, namely NYU-Depth-v2 and ScanNet, show that our method achieves state-of-the-art depth estimation results while using only a fraction of the number of parameters needed by the competing methods."

Establishing dense semantic correspondences requires dealing with large geometric variations caused by the unconstrained setting of images. To address such severe matching ambiguities, we introduce a novel approach, called {guided semantic flow}, based on the key insight that sparse yet reliable matches can effectively capture non-rigid geometric variations, and these confident matches can guide adjacent pixels to have similar solution spaces, reducing the matching ambiguities significantly. We realize this idea with learning-based selection of confident matches from an initial set of all pairwise matching scores and their propagation by a new differentiable upsampling layer based on moving least square concept. We take advantage of the guidance from reliable matches to refine the matching hypotheses through Gaussian parametric model in the subsequent matching pipeline. With the proposed method, state-of-the-art performance is attained on several standard benchmarks for semantic correspondence."

Person Re-identification (Re-ID) in crowed scenes is a challenging problem, where people are frequently partially occluded by objects and other people. However, few studies have provided flexible solutions to re-identifying people in an image containing a partial occlusion body part. In this paper, we propose a simple occlusion-aware approach to address the problem. The proposed method first leverages a fully convolutional network to generate spatial features. And then we design a combination of a pose-guided and mask-guided layer to generate saliency heatmap to further guide discriminative feature learning. More importantly, we propose a new matching approach, called Guided Adaptive Spatial Matching (GASM), which expects that each spatial feature in the query can find the most similar spatial features of a person in a gallery to match. Especially, We use the saliency heatmap to guide the adaptive spatial matching by assigning the foreground human parts with larger weights adaptively. The effectiveness of the proposed GASM is demonstrated on two occluded person datasets: Crowd REID (51.52\%) and Occluded REID (80.25\%) and three benchmark person datasets: Market1501 (95.31\%), DukeMTMC-reID (88.12\%) and MSMT17 (79.52\%). Additionally, GASM achieves good performance on cross-domain person Re-ID. The code and models are available at https://github.com/JDAI-CV/fast-reid/blob/master/projects/CrowdReID."

The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified approach. To address this limitation, in this study, we propose a guided deep decoder network as a general prior. The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image. The two networks are connected by feature refinement units to embed the multi-scale features of the guidance image into the deep decoder network. The proposed network allows the network parameters to be optimized in an unsupervised way without training data. Our results show that the proposed network can achieve state-of-the-art performance in various image fusion problems."

We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs. In addition, existing pixel-wise SSL approaches are only suitable for certain tasks as they usually require to use task-specific properties. In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. First, GCT addresses the issues caused by the dense outputs through a novel flaw detector. Second, the modules in GCT learn from unlabeled data collaboratively through two newly proposed constraints that are independent of task-specific properties. As a result, GCT can be applied to a wide range of pixel-wise tasks without structural adaptation. Our extensive experiments on four challenging vision tasks, including semantic segmentation, real image denoising, portrait image matting, and night image enhancement, show that GCT outperforms state-of-the-art SSL methods by a large margin."

Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information, conventional two-stage approaches utilizing structural information often lead to the problem of unreliable structural prediction and ambiguous image texture generation. In this paper, we propose a Semantic Guidance and Evaluation Network (SGE-Net) to iteratively update the structural priors and the inpainted image in an interplay framework of semantics extraction and image inpainting. It utilizes semantic segmentation map as guidance in each scale of inpainting, under which location-dependent inferences are re-evaluated, and, accordingly, poorly-inferred regions are refined in subsequent scales. Extensive experiments on real-world images of mixed scenes demonstrated the superiority of our proposed method over state-of-the-art approaches, in terms of clear boundaries and photo-realistic textures."

The Guesser is a task of visual grounding in GuessWhat?! like visual dialogue. It locates the target object in an image supposed by an Oracle oneself over a question-answer based dialogue between a Questioner and the Oracle. Most existing guessers make one and only one guess after receiving all question-answer pairs in a dialogue with the predefined number of rounds. This paper proposes a guessing state for the Guesser, and regards guess as a process with change of guessing state through a dialogue. A guessing state tracking based guess model is therefore proposed. The guessing state is defined as a distribution on objects in the image. With that in hand, two loss functions are defined as supervisions for model training. Early supervision brings supervision to Guesser at early rounds, and incremental supervision brings monotonicity to the guessing state. Experimental results on GuessWhat?! dataset show that our model significantly outperforms previous models, achieves new state-of-the-art, especially the success rate of guessing 83.3% is approaching the human-level accuracy of 84.4%."

In this paper, we propose a novel approach to predict group activities given the beginning frames with incomplete activity executions. Existing action prediction approaches learn to enhance the representation power of the partial observation. However, for group activity prediction, the relation evolution of people’s activity and their positions over time is an important cue for predicting group activity. To this end, we propose a sequential relational anticipation model (SRAM) that summarizes the relational dynamics in the partial observation and progressively anticipates the group representations with rich discriminative information. Our model explicitly anticipates both activity features and positions by two graph auto-encoders, aiming to learn a discriminative group representation for group activity prediction. Experimental results on two popularly used datasets demonstrate that our approach significantly outperforms the state-of-the-art activity prediction methods."

We introduce Grounded Situation Recognition (GSR), a task that requires producing structured semantic summaries of images describing: the primary activity, entities engaged in the activity with their roles (e.g. agent, tool), and bounding-box groundings of entities. GSR presents important technical challenges: identifying semantic saliency, categorizing and localizing a large and diverse set of entities, overcoming semantic sparsity, and disambiguating roles. Moreover, unlike in captioning, GSR is straightforward to evaluate. To study this new task we create the Situations With Groundings (SWiG) dataset which adds 278,336 bounding-box groundings to the 11,538 entity classes in the imsitu dataset. We propose a Joint Situation Localizer and find that jointly predicting situations and groundings with end-to-end training handily outperforms independent training with late fusion on the entire grounding metric suite with relative gains between 8% and 32%. Finally, we show initial findings on three exciting future directions enabled by our models: conditional querying, visual chaining, and grounded semantic aware image retrieval. Code and data available at https://prior.allenai.org/projects/gsr ."

We present a novel approach which is able to explore the configuration of grouped convolutions within neural networks. Group-size Series (GroSS) decomposition is a mathematical formulation of tensor factorisation into a series of approximations of increasing rank terms. GroSS allows for dynamic and differentiable selection of factorisation rank, which is analogous to a grouped convolution. Therefore, to the best of our knowledge, GroSS is the first method to enable simultaneous training of differing numbers of groups within a single layer, as well as all possible combinations between layers. In doing so, GroSS is able to train an entire grouped convolution architecture search-space concurrently. We demonstrate this through architecture searches with performance objectives on multiple datasets and networks. GroSS enables more effective and efficient search for grouped convolutional architectures."

Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly. In this paper, we aim to find a better approach to get more accurate localization results. We mainly put forward two suggestions for improvement: 1) different features and methods should be applied for rough and accurate localization, 2) relationship between keypoints should be considered. Specifically, we propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization subnet. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results. Experiments show that Graph-PCNN can be used in various backbones to boost the performance by a large margin. Without bells and whistles, our best model can achieve a new state-of-the-art 76.8% AP on COCO test-dev split. "

Human beings are fundamentally sociable --- that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has great potential for intelligent systems such as social chatbots and personal assistants. In this paper, we propose a simpler, faster, and more accurate method named graph relational reasoning network (GR$^2$N) for social relation recognition. Different from existing methods which process all social relations on an image independently, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Furthermore, the proposed GR$^2$N constructs several virtual relation graphs to explicitly grasp the strong logical constraints among different types of social relations. Experimental results illustrate that our method generates a reasonable and consistent social relation graph and improves the performance in both accuracy and efficiency."

In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss function. The GCN-inferred ""clean"" probability is then exploited as a relevance measure. Each noisy example is weighted by its relevance when learning a classifier for the end task. We evaluate our method on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data. Experimental results show that our GCN-based cleaning process significantly improves the classification accuracy over not cleaning the noisy data, as well as standard few-shot classification where only few clean examples are used."

Movie graphs play an important role to bridge heterogenous modalities of videos and texts in human-centric retrieval. In this work, we propose Graph Wasserstein Correlation Analysis (GWCA) to deal with the core issue therein, i.e, cross heterogeneous graph comparison. Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning. Such a seamless integration of graph signal filtering together with metric learning results in a surprise consistency on both learning processes, in which the goal of metric learning is just to optimize signal filters or vice versa. Further, we derive the solution of the graph comparison model as a classic generalized eigenvalue decomposition problem, which has an exactly closed-form solution. Finally, GWCA together with movie/text graphs generation are unified into the framework of movie retrieval to evaluate our proposed method. Extensive experiments on MovieGrpah dataset demonstrate the effectiveness of our GWCA as well as the entire framework. "