We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers specific to individual domains. Our key idea is to decompose discriminative representations in each domain into domain-agnostic and domain-specific components by learning a mixture of multiple normalization types. Because each domain has different characteristics, we optimize the mixture weights specialized to each domain and maximize the generalizability of the learned representations per domain. To this end, we incorporate instance normalization into the network with batch normalization since instance normalization is effective to discard the discriminative domain-specific representations. Since the joint optimization of the parameters in convolutional and normalization layers is not straightforward especially in the lower layers, the mixture weight of the normalization types is shared across all layers for the robustness of trained models. We analyze the effectiveness of the optimized normalization layers and demonstrate the state-of-the-art accuracy of our algorithm in the standard benchmark datasets in various settings.
We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns the final models using a multi-task classification loss for the source and target domains. Note that the two domains have separate batch normalization layers in both stages. Our framework can be easily incorporated into the domain adaptation techniques based on deep neural networks with batch normalization layers. We also present that our approach can be extended to the problem with multiple source domains. The proposed algorithm is evaluated on multiple benchmark datasets and achieves the state-of-the-art accuracy in the standard setting and the multi-source domain adaption scenario.
We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transferring knowledge from the objects belonging to semantically similar seen categories, we aim to understand the identity of the novel objects in an image surrounded by the known objects using the inter-object relation prior. Specifically, we leverage the visual context and the geometric relationships between all pairs of objects in a single image, and capture the information useful to infer unseen categories. We integrate our context-aware zero-shot learning framework into the traditional zero-shot learning techniques seamlessly using a Conditional Random Field (CRF). The proposed algorithm is evaluated on both zero-shot region classification and zero-shot detection tasks. The results on Visual Genome (VG) dataset show that our model significantly boosts performance with the additional visual context compared to traditional methods.
Dense video captioning is an extremely challenging task since accurate and coherent description of events in a video requires holistic understanding of video contents as well as contextual reasoning of individual events. Most existing approaches handle this problem by first detecting event proposals from a video and then captioning on a subset of the proposals. As a result, the generated sentences are prone to be redundant or inconsistent since they fail to consider temporal dependency between events. To tackle this challenge, we propose a novel dense video captioning framework, which models temporal dependency across events in a video explicitly and leverages visual and linguistic context from prior events for coherent storytelling. This objective is achieved by 1) integrating an event sequence generation network to select a sequence of event proposals adaptively, and 2) feeding the sequence of event proposals to our sequential video captioning network, which is trained by reinforcement learning with two-level rewards at both event and episode levels for better context modeling. The proposed technique achieves outstanding performances on ActivityNet Captions dataset in most metrics.
Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global transformation model that densely aligns one image to the other. Since an entire correlation map between all feature pairs across images is typically used to predict such a global transformation, noisy features from different backgrounds, clutter, and occlusion distract the predictor from correct estimation of the alignment. This is a challenging issue, in particular, in the problem of semantic correspondence where a large degree of image variations is often involved. In this paper, we introduce an attentive semantic alignment method that focuses on reliable correlations, filtering out distractors. For effective attention, we also propose an offset-aware correlation kernel that learns to capture translation-invariant local transformations in computing correlation values over spatial locations. Experiments demonstrate the effectiveness of the attentive model and offset-aware kernel, and the proposed model combining both techniques achieves the state-of-the-art performance.
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering. Existing large-scale visual data with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual concepts. However, it is not straightforward how the visual concepts should be captured and transferred to visual question answering models due to missing link between question dependent answering models and visual data without question or task specification. We tackle this problem in two steps: 1) learning a task conditional visual classifier based on unsupervised task discovery and 2) transferring and adapting the task conditional visual classifier to visual question answering models. Specifically, we employ linguistic knowledge sources such as structured lexical database (e.g. Wordnet) and visual descriptions for unsupervised task discovery, and adapt a learned task conditional visual classifier to answering unit in a visual question answering model. We empirically show that the proposed algorithm generalizes to unseen answers successfully using the knowledge transferred from the visual data.
We propose a generic framework to calibrate accuracy and confidence (score) of a prediction through stochastic inferences in deep neural networks. We first analyze relation between variation of multiple model parameters for a single example inference and variance of the corresponding prediction scores by Bayesian modeling of stochastic regularization. Our empirical observation shows that accuracy and score of a prediction are highly correlated with variance of multiple stochastic inferences given by stochastic depth or dropout. Motivated by these facts, we design a novel variance-weighted confidence-integrated loss function that is composed of two cross-entropy loss terms with respect to ground-truth and uniform distribution, which are balanced by variance of stochastic prediction scores. The proposed loss function enables us to learn deep neural networks that predict confidence calibrated scores using a single inference. Our algorithm presents outstanding confidence calibration performance and improves classification accuracy with two popular stochastic regularization techniques---stochastic depth and dropout---in multiple models and datasets; it alleviates overconfidence issue in deep neural networks significantly by training networks to achieve prediction accuracy proportional to confidence of prediction.
We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process over multiple layers of a convolutional neural network. The attentive process in each layer determines whether to pass or block features at certain spatial locations for use in the subsequent layers. The proposed progressive attention mechanism works well especially when combined with hard attention. We further employ local contexts to incorporate neighborhood features of each location and estimate a better attention probability map. The experiments on synthetic and real datasets show that the proposed attention networks outperform traditional attention methods in visual attribute prediction tasks.
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.