What makes free-hand sketches appealing for humans lies with its capability as a universal tool to depict the visual world. Such flexibility at human ease, however, introduces abstract renderings that pose unique challenges to computer vision models. In this paper, we propose a purpose-made sketch representation for human sketches. The key intuition is that such representation should be abstract at design, so to accommodate the abstract nature of sketches. This is achieved by interpreting sketch abstraction on two levels: appearance and structure. We abstract sketch structure as a pre-defined coarse-to-fine visual block hierarchy, and average visual features within each block to model appearance abstraction. We then discuss three general strategies on how to exploit feature synergy across different levels of this abstraction hierarchy. The superiority of explicitly abstracting sketch representation is empirically validated on a number of sketch analysis tasks, including sketch recognition, fine-grained sketch-based image retrieval, and generative sketch healing. Our simple design not only yields strong results on all said tasks, but also offers intuitive feature granularity control to tailor for various downstream tasks. Code will be made publicly available.
论文检索
输入标题、作者或关键词，从 1,526 篇学术成果中精准定位
A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these transformations rely on either a fixed vocabulary of pre-specified visual concepts, or on unsupervised disentanglement techniques whose alignment with human judgments about perceptual salience is unknown. This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built from three components: (1) automatic identification of perceptually salient directions based on their layer selectivity; (2) human annotation of these directions with free-form, compositional natural language descriptions; and (3) decomposition of these annotations into a visual concept vocabulary, consisting of distilled directions labeled with single words. Experiments show that concepts learned with our approach are reliable and composable--generalizing across classes, contexts, and observers, and enabling fine-grained manipulation of image style and content.
Communication between embodied AI agents has received increasing attention in recent years. Despite its use, it is still unclear whether the learned communication is interpretable and grounded in perception. To study the grounding of emergent forms of communication, we first introduce the collaborative multi-object navigation task 'CoMON.' In this task, an 'oracle agent' has detailed environment information in the form of a map. It communicates with a 'navigator agent' that perceives the environment visually and is tasked to find a sequence of goals. To succeed at the task, effective communication is essential. CoMON hence serves as a basis to study different communication mechanisms between heterogeneous agents, that is, agents with different capabilities and roles. We study two common communication mechanisms and analyze their communication patterns through an egocentric and spatial lens. We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment.
Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for end-to-end imitation learning models. NEAT is a continuous function which maps locations in Bird's Eye View (BEV) scene coordinates to waypoints and semantics, using intermediate attention maps to iteratively compress high-dimensional 2D image features into a compact representation. This allows our model to selectively attend to relevant regions in the input while ignoring information irrelevant to the driving task, effectively associating the images with the BEV representation. In a new evaluation setting involving adverse environmental conditions and challenging scenarios, NEAT outperforms several strong baselines and achieves driving scores on par with the privileged CARLA expert used to generate its training data. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.
Deep networks for Monocular Depth Estimation (MDE) have achieved promising performance recently and it is of great importance to further understand the interpretability of these networks. Existing methods attempt to provide post-hoc explanations by investigating visual cues, which may not explore the internal representations learned by deep networks. In this paper, we find that some hidden units of the network are selective to certain ranges of depth, and thus such behavior can be served as a way to interpret the internal representations. Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units. Moreover, we then propose a method to train interpretable MDE deep networks without changing their original architectures, by assigning a depth range for each unit to select. Experimental results demonstrate that our method is able to enhance the interpretability of deep MDE networks by largely improving the depth selectivity of their units, while not harming or even improving the depth estimation accuracy. We further provide comprehensive analysis to show the reliability of selective units, the applicability of our method on different models and layers, and a demonstration on monocular depth completion. We further provide comprehensive analysis to show the reliability of selective units, the applicability of our method on different layers, models, and datasets, and a demonstration on analysis of model error.
Despite the great progress of person re-identification (ReID) with the adoption of Convolutional Neural Networks, current ReID models are opaque and only outputs a scalar distance between two persons. There are few methods providing users semantically understandable explanations for why two persons are the same one or not. In this paper, we propose a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models. This is the first method to explore attributes to answer: 1) what and where the attributes make two persons different, and 2) how much each attribute contributes to the difference. In AMD, we design a pluggable interpreter network for target models to generate quantitative contributions of attributes and visualize accurate attention maps of the most discriminative attributes. To achieve this goal, we propose a metric distillation loss by which the interpreter learns to decompose the distance of two persons into components of attributes with knowledge distilled from the target model. Moreover, we propose an attribute prior loss to make the interpreter generate attribute-guided attention maps and to eliminate biases caused by the imbalanced distribution of attributes. This loss can guide the interpreter to focus on the exclusive and discriminative attributes rather than the large-area but common attributes of two persons. Comprehensive experiments show that the interpreter can generate effective and intuitive explanations for varied models and generalize well under cross-domain settings. As a by-product, the accuracy of target models can be further improved with our interpreter.
Self-Supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond
PDF ↗To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric characteristics, we propose to borrow self-supervised representation learning to facilitate geometric features discovery. To condense these features, we introduce an interpretable attention module, with the core of local maxima aggregation instead of fully automatic learning, whose mechanism is completely understandable and whose response map is physically reasonable. To the best of our knowledge, we are the first that perform self-supervised learning to discover geometric features. We conduct comprehensive experiments on three most popular datasets for vehicle ReID, i.e., VeRi-776, CityFlow-ReID, and VehicleID. We report our state-of-the-art (SOTA) performances and promising visualization results. We also show the excellent scalability of our approach on other ReID related tasks, i.e., person ReID and multi-target multi-camera (MTMC) vehicle tracking.
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support Samples
PDF ↗This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels. The pseudo-labels are generated non-parametrically, by comparing the representations of the image views to those of a set of randomly sampled labeled images. The distance between the view representations and labeled representations is used to provide a weighting over class labels, which we interpret as a soft pseudo-label. By non-parametrically incorporating labeled samples in this way, PAWS extends the distance-metric loss used in self-supervised methods such as BYOL and SwAV to the semi-supervised setting. Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75% and 66% top-1 respectively. This is achieved with only 200 epochs of training, which is 4x less than the previous best method.
Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual or a small number of images. To facilitate human understandability and generalization ability, it is important to develop representative interpretations that interpret common decision logics of a CNN on a large group of similar images, which reveal the common semantics data contributes to many closely related predictions. In this paper, we develop a novel unsupervised approach to produce a highly representative interpretation for a large number of similar images. We formulate the problem of finding representative interpretations as a co-clustering problem, and convert it into a submodular cost submodular cover problem based on a sample of the linear decision boundaries of a CNN. We also present a visualization and similarity ranking method. Our extensive experiments demonstrate the excellent performance of our method.
Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with the task of using this data to learn to localize (or to ground) arbitrary text phrases in images without any additional annotations. However, most recent SotA methods for WSG assume an existence of a pre-trained object detector, relying on it to produce the ROIs for localization. In this work, we focus on the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained detector. We directly learn everything from the images and associated free-form text pairs, thus potentially gaining advantage on the categories unsupported by the detector. The key idea behind our proposed Grounding by Separation (GbS) method is synthesizing `text to image-regions' associations by random alpha-blending of arbitrary image pairs and using the corresponding texts of the pair as conditions to recover the alpha map from the blended image via a segmentation network. At test time, this allows using the query phrase as a condition for a non-blended query image, thus interpreting the test image as a composition of a region corresponding to the phrase and the complement region. Using this approach we demonstrate a significant accuracy improvement, up to 8.5% over previous DF-WSG SotA, for a range of benchmarks including Flickr30K, Visual Genome, and ReferIt, as well as a significant complementary improvement (above 7%) over the detector-based approaches for WSG.
We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual exam- ples, we prove that distilling from these virtual examples is equivalent to label distribution learning under certain con- straints. We show that when the virtual example distribu- tion becomes flatter than the original input distribution, the under-represented tail classes will receive significant im- provements, which is crucial in long-tailed recognition. The proposed DiVE method can explicitly tune the virtual exam- ple distribution to become flat. Extensive experiments on three benchmark datasets, including the large-scale iNat- uralist ones, justify that the proposed DiVE method can significantly outperform state-of-the-art methods. Further- more, additional analyses and experiments verify the virtual example interpretation, and demonstrate the effectiveness of tailored designs in DiVE for long-tailed problems.
Hand gesture serves as a critical role in sign language. Current deep-learning-based sign language recognition (SLR) methods may suffer insufficient interpretability and overfitting due to limited sign data sources. In this paper, we introduce the first self-supervised pre-trainable SignBERT with incorporated hand prior for SLR. SignBERT views the hand pose as a visual token, which is derived from an off-the-shelf pose extractor. The visual tokens are then embedded with gesture state, temporal and hand chirality information. To take full advantage of available sign data sources, SignBERT first performs self-supervised pre-training by masking and reconstructing visual tokens. Jointly with several mask modeling strategies, we attempt to incorporate hand prior in a model-aware method to better model hierarchical context over the hand sequence. Then with the prediction head added, SignBERT is fine-tuned to perform the downstream SLR task. To validate the effectiveness of our method on SLR, we perform extensive experiments on four public benchmark datasets, i.e., NMFs-CSL, SLR500, MSASL and WLASL. Experiment results demonstrate the effectiveness of both self-supervised learning and imported hand prior. Furthermore, we achieve state-of-the-art performance on all benchmarks with a notable gain.
The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
PDF ↗Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas. Most existing methods take the words in the instructions and the discrete views of each panorama as the minimal unit of encoding. However, this requires a model to match different nouns (e.g., TV, table) against the same input view feature. In this work, we propose an object-informed sequential BERT to encode visual perceptions and linguistic instructions at the same fine-grained level, namely objects and words. Our sequential BERT also enables the visual-textual clues to be interpreted in light of the temporal context, which is crucial to multi-round VLN tasks. Additionally, we enable the model to identify the relative direction (e.g., left/right/front/back) of each navigable location and the room type (e.g., bedroom, kitchen) of its current and final navigation goal, as such information is widely mentioned in instructions implying the desired next and final locations. We thus enable the model to know-where the objects lie in the images, and to know-where they stand in the scene. Extensive experiments demonstrate the effectiveness compared against several state-of-the-art methods on three indoor VLN tasks: REVERIE, NDH, and R2R. Project repository: https://github.com/YuankaiQi/ORIST
Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified.
Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the explanations could be manipulated easily by adding visually imperceptible perturbations to the input while keeping the model's prediction intact. In this work, we study the problem of attributional robustness (i.e. models having robust explanations) by showing an upper bound for attributional vulnerability in terms of spatial correlation between the input image and its explanation map. We propose a training methodology that learns robust features by minimizing this upper bound using soft-margin triplet loss. Our methodology of robust attribution training (ART) achieves the new state-of-the-art attributional robustness measure by a margin of $pprox$ 6-18 $\%$ on several standard datasets, ie. SVHN, CIFAR-10 and GTSRB. We further show the utility of the proposed robust training technique (ART) in the downstream task of weakly supervised object localization by achieving the new state-of-the-art performance on CUB-200 dataset.
Deep neural networks are generally considered black-box models that offer less interpretability for their decision process. To address this limitation, Class Activation Map (CAM) provides an attractive solution that visualizes class-specific discriminative regions in an input image. The remarkable ability of CAMs to locate class discriminating regions has been exploited in weakly-supervised segmentation and localization tasks. In this work, we explore a new direction towards the possible use of CAM in deep network learning process. We note that such visualizations lend insights into the workings of deep CNNs and could be leveraged to introduce additional constraints during the learning stage. Specifically, the CAMs for negative classes (negative CAMs) often have false activations even though those classes are absent from an image. Thereby, we propose a loss function that seeks to minimize peaks within the negative CAMs, called Homogeneous Negative CAM loss. This way, in an effort to fix localization errors, our loss provides an extra supervisory signal that helps the model to better discriminate between similar classes. Our designed loss function is easy to implement and can be readily integrated into existing DNNs. We evaluate it on a number of classification tasks including large-scale recognition, multi-label classification and fine-grained recognition. Our loss provides better performance compared to other loss functions across the studied tasks. Additionally, we show that the proposed loss function provides higher robustness against adversarial attacks and noisy labels.
Convolutional neural networks (CNNs) have achieved superior accuracy in many visual related tasks. However, the inference process through intermediate layers is opaque, making it difficult to interpret such networks or develop trust in their operation. We propose to model the network hidden layers activity using probabilistic models. The activity patterns in layers of interest are modeled as Gaussian mixture models, and transition probabilities between clusters in consecutive modeled layers are estimated. Based on maximum-likelihood considerations, a subset of the nodes and paths relevant for network prediction are chosen, connected, and visualized as an inference graph. We show that such graphs are useful for understanding the general inference process of a class, as well as explaining decisions the network makes regarding specific images. In addition, the models provide an interesting observation regarding the highly local nature of column activities in top CNN layers.
Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image. In previous works, relations were identified by solving an assignment problem formulated as Mixed-Integer Linear Programs. In this work, we interpret that formulation as Ordinary Differential Equation (ODE). The proposed architecture performs scene graph inference by solving a neural variant of an ODE by end-to-end learning. It achieves state-of-the-art results on all three benchmark tasks: scene graph generation (SGGen), classification (SGCls) and visual relationship detection (PredCls) on Visual Genome benchmark.
While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based regression, which entails predicting a confidence value for each input-target pair $(x, y)$. While this approach has demonstrated impressive results, it requires important task-dependent design choices, and the predicted confidences lack a natural probabilistic meaning. We address these issues by proposing a general and conceptually simple regression method with a clear probabilistic interpretation. In our proposed approach, we create an energy-based model of the conditional target density $p(y | x)$, using a deep neural network to predict the un-normalized density from $(x, y)$. This model of $p(y | x)$ is trained by directly minimizing the associated negative log-likelihood, approximated using Monte Carlo sampling. We perform comprehensive experiments on four computer vision regression tasks. Our approach outperforms direct regression, as well as other probabilistic and confidence-based methods. Notably, our model achieves a $2.2\%$ AP improvement over Faster-RCNN for object detection on the COCO dataset, and sets a new state-of-the-art on visual tracking when applied for bounding box estimation. In contrast to confidence-based methods, our approach is also shown to be directly applicable to more general tasks such as age and head-pose estimation. Code is available at https://github.com/fregu856/ebms_regression.
Prior studies show that the key to face anti-spoofing lies in the subtle image pattern, termed “spoof trace”, e.g., color distortion, 3D mask edge, Moir´e pattern, and many others. Designing a generic anti-spoofing model to estimate those spoof traces can improve not only the generalization of the spoof detection, but also the interpretability of the model’s decision. Yet, this is a challenging task due to the diversity of spoof types and the lack of ground truth in spoof traces. This work designs a novel adversarial learning framework to disentangle the spoof traces from input faces as a hierarchical combination of patterns at multiple scales. With the disentangled spoof traces, we unveil the live counterpart of the original spoof face, and further synthesize realistic new spoof faces after a proper geometric correction. Our method demonstrates superior spoof detection performance on both seen and unseen spoof scenarios while providing visually-convincing estimation of spoof traces. Code is available at https://github.com/yaojieliu/ECCV20-STDN.