State-of-the-art crowd counting models follow an encoder-decoder approach. Images are first processed by the encoder to extract features. Then, to account for perspective distortion, the highest-level feature map is fed to extra components to extract multiscale features, which are the input to the decoder to generate crowd densities. However, in these methods, features extracted at earlier stages during encoding are underutilised, and the multiscale modules can only capture a limited range of receptive fields, albeit with considerable computational cost. This paper proposes a novel crowd counting architecture (FusionCount), which exploits the adaptive fusion of a large majority of encoded features instead of relying on additional extraction components to obtain multiscale features. Thus, it can cover a more extensive scope of receptive field sizes and lower the computational cost. We also introduce a new channel reduction block, which can extract saliency information during decoding and further enhance the model's performance. Experiments on two benchmark databases demonstrate that our model achieves state-of-the-art results with reduced computational complexity.
Current state-of-the-art trackers only rely on a target appearance model in order to localize the object in each frame. Such approaches are however prone to fail in case of e.g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking. Having the knowledge about the presence and locations of other objects in the surrounding scene can be highly beneficial in such cases. This scene information can be propagated through the sequence and used to, for instance, explicitly avoid distractor objects and eliminate target candidate regions. In this work, we propose a novel tracking architecture which can utilize scene information for tracking. Our tracker represents such information as dense localized state vectors, which can encode, for example, if the local region is target, background, or distractor. These state vectors are propagated through the sequence and combined with the appearance model output to localize the target. Our network is learned to effectively utilize the scene information by directly maximizing tracking performance on video segments. The proposed approach sets a new state-of-the-art on 3 tracking benchmarks, achieving an AO score of 63.6% on the recent GOT-10k dataset.
Multi-scale architectures have shown effectiveness in a variety of tasks including single image denoising, thanks to appealing cross-scale complementarity. However, existing methods treat different scale features equally without considering their scale-specific characteristics, i.e., the within-scale characteristics are ignored. In this paper, we reveal this missing piece for multi-scale architecture design and accordingly propose a novel Multi-Scale Adaptive Network (MSANet) for single image denoising. To be specific, MSANet simultaneously embraces the within-scale characteristics and the cross-scale complementarity thanks to three novel neural blocks, i.e., adaptive feature block (AFeB), adaptive multi-scale block (AMB), and adaptive fusion block (AFuB). In brief, AFeB is designed to adaptively select details and filter noises, which is highly expected for fine-grained features. AMB could enlarge the receptive field and aggregate the multi-scale information, which is designed to satisfy the demands of both fine- and coarse-grained features. AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which is used to fuse the features with varying characteristics from coarse to fine. Extensive experiments on both three real and six synthetic noisy image datasets show the superiority of MSANet compared with 12 methods.
A common misconception among blockchain users is that pseudonymity guarantees privacy. The reality is almost the opposite. Every transaction one makes is recorded on a public ledger and reveals information about one's identity. Mixers, such as Tornado Cash, were developed to preserve privacy through "mixing" transactions with those of others in an anonymity pool, making it harder to link deposits and withdrawals from the pool. Unfortunately, it is still possible to reveal information about those in the anonymity pool if users are not careful. We introduce Tutela, an application built on expert heuristics to report the true anonymity of an Ethereum address. In particular, Tutela has three functionalities: first, it clusters together Ethereum addresses based on interaction history such that for an Ethereum address, we can identify other addresses likely owned by the same entity; second, it shows Ethereum users their potentially compromised transactions; third, Tutela computes the true size of the anonymity pool of each Tornado Cash mixer by excluding potentially compromised transactions. A public implementation of Tutela can be found at https://github.com/TutelaLabs/tutela-app. To use Tutela, visit https://www.tutela.xyz.
Few-shot segmentation enables the model to recognize unseen classes with few annotated examples. Most existing methods adopt prototype learning architecture, where support prototype vectors are expanded and concatenated with query features to perform conditional segmentation. However, such framework potentially focuses more on query features while may neglect the similarity between support and query features. This paper proposes a contrastive enhancement approach using latent prototypes to leverage latent classes and raise the utilization of similarity information between prototype and query features. Specifically, a latent prototype sampling module is proposed to generate pseudo-mask and novel prototypes based on features similarity. The module conveniently conducts end-to-end learning and has no strong dependence on clustering numbers like cluster-based method. Besides, a contrastive enhancement module is developed to drive models to provide different predictions with the same query features. Our method can be used as an auxiliary module to flexibly integrate into other baselines for a better segmentation performance. Extensive experiments show our approach remarkably improves the performance of state-of-the-art methods for 1-shot and 5-shot segmentation, especially outperforming baseline by 5.9% and 7.3% for 5-shot task on Pascal-5^i and COCO-20^i. Source code is available at https://github.com/zhaoxiaoyu1995/CELP-Pytorch
Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence estimates that accurately reflect the contributions of sub-populations to the overall divergence. We model the sub-populations coming from a rich (possibly infinite) family $\mathcal{C}$ of overlapping subsets of the domain. We propose the notion of multi-group attribution for $\mathcal{C}$, which requires that the estimated divergence conditioned on every sub-population in $\mathcal{C}$ satisfies some natural accuracy and fairness desiderata, such as ensuring that sub-populations where the model predicts significant divergence do diverge significantly in the two distributions. Our main technical contribution is to show that multi-group attribution can be derived from the recently introduced notion of multi-calibration for importance weights [HKRR18, GRSW21]. We provide experimental evidence to support our theoretical results, and show that multi-group attribution provides better KL divergence estimates when conditioned on sub-populations than other popular algorithms.
Vision transformers (ViTs) have gained increasing popularity as they are commonly believed to own higher modeling capacity and representation flexibility, than traditional convolutional networks. However, it is questionable whether such potential has been fully unleashed in practice, as the learned ViTs often suffer from over-smoothening, yielding likely redundant models. Recent works made preliminary attempts to identify and alleviate such redundancy, e.g., via regularizing embedding similarity or re-injecting convolution-like structures. However, a "head-to-toe assessment" regarding the extent of redundancy in ViTs, and how much we could gain by thoroughly mitigating such, has been absent for this field. This paper, for the first time, systematically studies the ubiquitous existence of redundancy at all three levels: patch embedding, attention map, and weight space. In view of them, we advocate a principle of diversity for training ViTs, by presenting corresponding regularizers that encourage the representation diversity and coverage at each of those levels, that enabling capturing more discriminative information. Extensive experiments on ImageNet with a number of ViT backbones validate the effectiveness of our proposals, largely eliminating the observed ViT redundancy and significantly boosting the model generalization. For example, our diversified DeiT obtains 0.70%~1.76% accuracy boosts on ImageNet with highly reduced similarity. Our codes are fully available in https://github.com/VITA-Group/Diverse-ViT.
In this paper we discuss the problem of authentication of forensic audio when using digital recordings. Although forensic audio has been addressed in several papers the existing approaches are focused on analog magnetic recordings, which are becoming old-fashion due to the large amount of digital recorders available on the market (optical, solid-state, hard disks, etc). We present an approach based on digital signal processing that consist of spread spectrum techniques for speech watermarking. This approach presents the advantage that the authentication is based on the signal itself rather than the recording support. Thus, it is valid for whatever recording device. In addition, our proposal permits the introduction of relevant information such as recording date and time and all the relevant data (this is not possible with classical systems). Our experimental results reveal that the speech watermarking procedure does not interfere in a significant way with the posterior forensic speaker identification.
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations Challenge of DSTC-10. In order to mitigate the discrepancies between spoken and written text, we mainly employ extensive data augmentation strategies on written data, including artificial error injection and round-trip text-speech transformation. To train robust models for spoken conversations, we improve pre-trained language models, and apply ensemble algorithms for each sub-task. Typically, for the detection task, we fine-tune \roberta and ELECTRA, and run an error-fixing ensemble algorithm. For the selection task, we adopt a two-stage framework that consists of entity tracking and knowledge ranking, and propose a multi-task learning method to learn multi-level semantic information by domain classification and entity selection. For the generation task, we adopt a cross-validation data process to improve pre-trained generative language models, followed by a consensus decoding algorithm, which can add arbitrary features like relative \rouge metric, and tune associated feature weights toward \bleu directly. Our approach ranks third on the objective evaluation and second on the final official human evaluation.
We propose a new benchmark for evaluating stereoscopic visual-inertial computer vision algorithms (SLAM/ SfM/ 3D Reconstruction/ Visual-Inertial Odometry) for minimally invasive surgical (MIS) interventions in the abdomen. Our MITI Dataset available at [https://mediatum.ub.tum.de/1621941] provides all the necessary data by a complete recording of a handheld surgical intervention at Research Hospital Rechts der Isar of TUM. It contains multimodal sensor information from IMU, stereoscopic video, and infrared (IR) tracking as ground truth for evaluation. Furthermore, calibration for the stereoscope, accelerometer, magnetometer, the rigid transformations in the sensor setup, and time-offsets are available. We wisely chose a suitable intervention that contains very few cutting and tissue deformation and shows a full scan of the abdomen with a handheld camera such that it is ideal for testing SLAM algorithms. Intending to promote the progress of visual-inertial algorithms designed for MIS application, we hope that our clinical training dataset helps and enables researchers to enhance algorithms.