Unsupervised Collaborative Metric Learning with Mixed-Scale Groups for General Object Retrieval

The task of searching for visual objects in a large image dataset is difficult because it requires efficient matching and accurate localization of objects that can vary in size. Although the segment anything model (SAM) offers a potential solution for extracting object spatial context, learning embeddings for local objects remains a challenging problem. This paper presents a novel unsupervised deep metric learning approach, termed unsupervised collaborative metric learning with mixed-scale groups (MS-UGCML), devised to learn embeddings for objects of varying scales. Following this, a benchmark of challenges is assembled by utilizing COCO 2017 and VOC 2007 datasets to facilitate the training and evaluation of general object retrieval models. Finally, we conduct comprehensive ablation studies and discuss the complexities faced within the domain of general object retrieval. Our object retrieval evaluations span a range of datasets, including BelgaLogos, Visual Genome, LVIS, in addition to a challenging evaluation set that we have individually assembled for open-vocabulary evaluation. These comprehensive evaluations effectively highlight the robustness of our unsupervised MS-UGCML approach, with an object level and image level mAPs improvement of up to 6.69% and 10.03%, respectively. The code is publicly available at https://github.com/dengyuhai/MS-UGCML.

What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

Parrot-Trained Adversarial Examples: Pushing the Practicality of Black-Box Audio Attacks against Speaker Recognition Models

Audio adversarial examples (AEs) have posed significant security challenges to real-world speaker recognition systems. Most black-box attacks still require certain information from the speaker recognition model to be effective (e.g., keeping probing and requiring the knowledge of similarity scores). This work aims to push the practicality of the black-box attacks by minimizing the attacker's knowledge about a target speaker recognition model. Although it is not feasible for an attacker to succeed with completely zero knowledge, we assume that the attacker only knows a short (or a few seconds) speech sample of a target speaker. Without any probing to gain further knowledge about the target model, we propose a new mechanism, called parrot training, to generate AEs against the target model. Motivated by recent advancements in voice conversion (VC), we propose to use the one short sentence knowledge to generate more synthetic speech samples that sound like the target speaker, called parrot speech. Then, we use these parrot speech samples to train a parrot-trained(PT) surrogate model for the attacker. Under a joint transferability and perception framework, we investigate different ways to generate AEs on the PT model (called PT-AEs) to ensure the PT-AEs can be generated with high transferability to a black-box target model with good human perceptual quality. Real-world experiments show that the resultant PT-AEs achieve the attack success rates of 45.8% - 80.8% against the open-source models in the digital-line scenario and 47.9% - 58.3% against smart devices, including Apple HomePod (Siri), Amazon Echo, and Google Home, in the over-the-air scenario.

You Only Forward Once: Prediction and Rationalization in A Single Forward Pass

Unsupervised rationale extraction aims to extract concise and contiguous text snippets to support model predictions without any annotated rationale. Previous studies have used a two-phase framework known as the Rationalizing Neural Prediction (RNP) framework, which follows a generate-then-predict paradigm. They assumed that the extracted explanation, called rationale, should be sufficient to predict the golden label. However, the assumption above deviates from the original definition and is too strict to perform well. Furthermore, these two-phase models suffer from the interlocking problem and spurious correlations. To solve the above problems, we propose a novel single-phase framework called You Only Forward Once (YOFO), derived from a relaxed version of rationale where rationales aim to support model predictions rather than make predictions. In our framework, A pre-trained language model like BERT is deployed to simultaneously perform prediction and rationalization with less impact from interlocking or spurious correlations. Directly choosing the important tokens in an unsupervised manner is intractable. Instead of directly choosing the important tokens, YOFO gradually removes unimportant tokens during forward propagation. Through experiments on the BeerAdvocate and Hotel Review datasets, we demonstrate that our model is able to extract rationales and make predictions more accurately compared to RNP-based models. We observe an improvement of up to 18.4\% in token-level F1 compared to previous state-of-the-art methods. We also conducted analyses and experiments to explore the extracted rationales and token decay strategies. The results show that YOFO can extract precise and important rationales while removing unimportant tokens in the middle part of the model.

Breaking the Complexity Barrier in Compositional Minimax Optimization

Compositional minimax optimization is a pivotal yet under-explored challenge across machine learning, including distributionally robust training and policy evaluation for reinforcement learning. Current techniques exhibit suboptimal complexity or rely heavily on large batch sizes. This paper proposes Nested STOchastic Recursive Momentum (NSTORM), attaining the optimal sample complexity of $O(\kappa^3/\epsilon^3)$ for finding an $\epsilon$-accurate solution. However, NSTORM requires low learning rates, potentially limiting applicability. Thus we introduce ADAptive NSTORM (ADA-NSTORM) with adaptive learning rates, proving it achieves the same sample complexity while experiments demonstrate greater effectiveness. Our methods match lower bounds for minimax optimization without large batch requirements, validated through extensive experiments. This work significantly advances compositional minimax optimization, a crucial capability for distributional robustness and policy evaluation

Inter-Instance Similarity Modeling for Contrastive Learning

The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential representation degeneration. In this paper, we propose a novel image mix method, PatchMix, for contrastive learning in Vision Transformer (ViT), to model inter-instance similarities among images. Following the nature of ViT, we randomly mix multiple images from mini-batch in patch level to construct mixed image patch sequences for ViT. Compared to the existing sample mix methods, our PatchMix can flexibly and efficiently mix more than two images and simulate more complicated similarity relations among natural images. In this manner, our contrastive framework can significantly reduce the gap between contrastive objective and ground truth in reality. Experimental results demonstrate that our proposed method significantly outperforms the previous state-of-the-art on both ImageNet-1K and CIFAR datasets, e.g., 3.0% linear accuracy improvement on ImageNet-1K and 8.7% kNN accuracy improvement on CIFAR100. Moreover, our method achieves the leading transfer performance on downstream tasks, object detection and instance segmentation on COCO dataset. The code is available at https://github.com/visresearch/patchmix

Data-Driven Next-Generation Wireless Networking: Embracing AI for Performance and Security

New network architectures, such as the Internet of Things (IoT), 5G, and next-generation (NextG) cellular systems, put forward emerging challenges to the design of future wireless networks toward ultra-high data rate, massive data processing, smart designs, low-cost deployment, reliability and security in dynamic environments. As one of the most promising techniques today, artificial intelligence (AI) is advocated to enable a data-driven paradigm for wireless network design. In this paper, we are motivated to review existing AI techniques and their applications for the full wireless network protocol stack toward improving network performance and security. Our goal is to summarize the current motivation, challenges, and methodology of using AI to enhance wireless networking from the physical to the application layer, and shed light on creating new AI-enabled algorithms, mechanisms, protocols, and system designs for future data-driven wireless networking.

Modeling Global Distribution for Federated Learning with Label Distribution Skew

Federated learning achieves joint training of deep models by connecting decentralized data sources, which can significantly mitigate the risk of privacy leakage. However, in a more general case, the distributions of labels among clients are different, called ``label distribution skew''. Directly applying conventional federated learning without consideration of label distribution skew issue significantly hurts the performance of the global model. To this end, we propose a novel federated learning method, named FedMGD, to alleviate the performance degradation caused by the label distribution skew issue. It introduces a global Generative Adversarial Network to model the global data distribution without access to local datasets, so the global model can be trained using the global information of data distribution without privacy leakage. The experimental results demonstrate that our proposed method significantly outperforms the state-of-the-art on several public benchmarks. Code is available at \url{https://github.com/Sheng-T/FedMGD}.

Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception

Recently, adversarial machine learning attacks have posed serious security threats against practical audio signal classification systems, including speech recognition, speaker recognition, and music copyright detection. Previous studies have mainly focused on ensuring the effectiveness of attacking an audio signal classifier via creating a small noise-like perturbation on the original signal. It is still unclear if an attacker is able to create audio signal perturbations that can be well perceived by human beings in addition to its attack effectiveness. This is particularly important for music signals as they are carefully crafted with human-enjoyable audio characteristics. In this work, we formulate the adversarial attack against music signals as a new perception-aware attack framework, which integrates human study into adversarial attack design. Specifically, we conduct a human study to quantify the human perception with respect to a change of a music signal. We invite human participants to rate their perceived deviation based on pairs of original and perturbed music signals, and reverse-engineer the human perception process by regression analysis to predict the human-perceived deviation given a perturbed signal. The perception-aware attack is then formulated as an optimization problem that finds an optimal perturbation signal to minimize the prediction of perceived deviation from the regressed human perception model. We use the perception-aware framework to design a realistic adversarial music attack against YouTube's copyright detector. Experiments show that the perception-aware attack produces adversarial music with significantly better perceptual quality than prior work.