In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important tool of regularizing the distribution, batch normalization (BN) has been widely used in existing methods. However, they neglect that BN is severely biased to the training domain and inevitably suffers the performance drop if directly generalized without being updated. To tackle this issue, we propose Batch Norm Test-time Adaption (BNTA), a novel re-id framework that applies the self-supervised strategy to update BN parameters adaptively. Specifically, BNTA quickly explores the domain-aware information within unlabeled target data before inference, and accordingly modulates the feature distribution normalized by BN to adapt to the target domain. This is accomplished by two designed self-supervised auxiliary tasks, namely part positioning and part nearest neighbor matching, which help the model mine the domain-aware information with respect to the structure and identity of body parts, respectively. To demonstrate the effectiveness of our method, we conduct extensive experiments on three re-id datasets and confirm the superior performance to the state-of-the-art methods.
We develop a structural econometric model to capture the decision dynamics of human evaluators on an online micro-lending platform, and estimate the model parameters using a real-world dataset. We find two types of biases in gender, preference-based bias and belief-based bias, are present in human evaluators' decisions. Both types of biases are in favor of female applicants. Through counterfactual simulations, we quantify the effect of gender bias on loan granting outcomes and the welfare of the company and the borrowers. Our results imply that both the existence of the preference-based bias and that of the belief-based bias reduce the company's profits. When the preference-based bias is removed, the company earns more profits. When the belief-based bias is removed, the company's profits also increase. Both increases result from raising the approval probability for borrowers, especially male borrowers, who eventually pay back loans. For borrowers, the elimination of either bias decreases the gender gap of the true positive rates in the credit risk evaluation. We also train machine learning algorithms on both the real-world data and the data from the counterfactual simulations. We compare the decisions made by those algorithms to see how evaluators' biases are inherited by the algorithms and reflected in machine-based decisions. We find that machine learning algorithms can mitigate both the preference-based bias and the belief-based bias.
Superpixels have been widely used in computer vision tasks due to their representational and computational efficiency. Meanwhile, deep learning and end-to-end framework have made great progress in various fields including computer vision. However, existing superpixel algorithms cannot be integrated into subsequent tasks in an end-to-end way. Traditional algorithms and deep learning-based algorithms are two main streams in superpixel segmentation. The former is non-differentiable and the latter needs a non-differentiable post-processing step to enforce connectivity, which constraints the integration of superpixels and downstream tasks. In this paper, we propose a deep learning-based superpixel segmentation algorithm SIN which can be integrated with downstream tasks in an end-to-end way. Owing to some downstream tasks such as visual tracking require real-time speed, the speed of generating superpixels is also important. To remove the post-processing step, our algorithm enforces spatial connectivity from the start. Superpixels are initialized by sampled pixels and other pixels are assigned to superpixels through multiple updating steps. Each step consists of a horizontal and a vertical interpolation, which is the key to enforcing spatial connectivity. Multi-layer outputs of a fully convolutional network are utilized to predict association scores for interpolations. Experimental results show that our approach runs at about 80fps and performs favorably against state-of-the-art methods. Furthermore, we design a simple but effective loss function which reduces much training time. The improvements of superpixel-based tasks demonstrate the effectiveness of our algorithm. We hope SIN will be integrated into downstream tasks in an end-to-end way and benefit the superpixel-based community. Code is available at: \href{https://github.com/yuanqqq/SIN}{https://github.com/yuanqqq/SIN}.
In recent years, single image dehazing models (SIDM) based on atmospheric scattering model (ASM) have achieved remarkable results. However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image. Obviously, the hazy images taken in real world cannot always satisfy this assumption. Such generating modelling mismatch between the real-world images and ASM sets up the upper bound of trained ASM-based SIDM for dehazing. Bearing this in mind, in this study, a new fully non-homogeneous atmospheric scattering model (FNH-ASM) is proposed for well modeling the hazy images under complex conditions where ALF and ASC are pixel dependent. However, FNH-ASM brings difficulty in practical application. In FNH-ASM based SIDM, the estimation bias of parameters at different positions lead to different distortion of dehazing result. Hence, in order to reduce the influence of parameter estimation bias on dehazing results, two new cost sensitive loss functions, beta-Loss and D-Loss, are innovatively developed for limiting the parameter bias of sensitive positions that have a greater impact on the dehazing result. In the end, based on FNH-ASM, an end-to-end CNN-based dehazing network, FNHD-Net, is developed, which applies beta-Loss and D-Loss. Experimental results demonstrate the effectiveness and superiority of our proposed FNHD-Net for dehazing on both synthetic and real-world images. And the performance improvement of our method increases more obviously in dense and heterogeneous haze scenes.
Vision and Language Navigation (VLN) requires an agent to navigate to a target location by following natural language instructions. Most of existing works represent a navigation candidate by the feature of the corresponding single view where the candidate lies in. However, an instruction may mention landmarks out of the single view as references, which might lead to failures of textual-visual matching of existing methods. In this work, we propose a multi-module Neighbor-View Enhanced Model (NvEM) to adaptively incorporate visual contexts from neighbor views for better textual-visual matching. Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views. The subject module fuses neighbor views at a global level, and the reference module fuses neighbor objects at a local level. Subjects and references are adaptively determined via attention me'chanisms. Our model also includes an action module to utilize the strong orientation guidance (e.g., "turn left") in instructions. Each module predicts navigation action separately and their weighted sum is used for predicting the final action. Extensive experimental results demonstrate the effectiveness of the proposed method on the R2R and R4R benchmarks against several state-of-the-art navigators, and NvEM even beats some pre-training ones. Our code is available at https://github.com/MarSaKi/NvEM.
Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, \ie $1/4$, $1/8$, $1/16$, and $1/32$ of the input image. There are two drawbacks of this strategy: 1) feature maps of different spatial sizes may be not well aligned spatially, which potentially hurts the accuracy of keypoint location; 2) these scales are fixed and inflexible, which may restrict the generalization ability over various human sizes. Towards these issues, we propose an adaptive dilated convolution (ADC). It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels. More importantly, these dilation rates are generated by a regression module. It enables ADC to adaptively adjust the fused scales and thus ADC may generalize better to various human sizes. ADC can be end-to-end trained and easily plugged into existing methods. Extensive experiments show that ADC can bring consistent improvements to various HPE methods. The source codes will be released for further research.
With the rise of voice chat rooms, a gigantic resource of data can be exposed to the research community for natural language processing tasks. Moderators in voice chat rooms actively monitor the discussions and remove the participants with offensive language. However, it makes the hate speech detection even more difficult since some participants try to find creative ways to articulate hate speech. This makes the hate speech detection challenging in new social media like Clubhouse. To the best of our knowledge all the hate speech datasets have been collected from text resources like Twitter. In this paper, we take the first step to collect a significant dataset from Clubhouse as the rising star in social media industry. We analyze the collected instances from statistical point of view using the Google Perspective Scores. Our experiments show that, the Perspective Scores can outperform Bag of Words and Word2Vec as high level text features.