Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving

Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this paper, we explore vulnerabilities of MDE algorithms in AD systems, presenting LensAttack, a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of LensAttack on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that LensAttack can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.

Optical Lens Attack on Deep Learning Based Monocular Depth Estimation

Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a detected obstacle or changing lanes to avoid collision. In this paper, we investigate the security risks associated with monocular vision-based depth estimation algorithms utilized by AD systems. By exploiting the vulnerabilities of MDE and the principles of optical lenses, we introduce LensAttack, a physical attack that involves strategically placing optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We begin by constructing a mathematical model of our attack, incorporating various attack parameters. Subsequently, we simulate the attack and evaluate its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models. The results highlight the significant impact of LensAttack on the accuracy of depth estimation in AD systems.

EA-VTR: Event-Aware Video-Text Retrieval

Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to dual-encoder provides a natural approach to harness their strengths. Thus we investigate the following valuable question: how to make cross-encoder a good teacher for dual-encoder? Our findings are threefold:(1) Cross-modal similarity score distribution of cross-encoder is more concentrated while the result of dual-encoder is nearly normal making vanilla logit distillation less effective. However ranking distillation remains practical as it is not affected by the score distribution.(2) Only the relative order between hard negatives conveys valid knowledge while the order information between easy negatives has little significance.(3) Maintaining the coordination between distillation loss and dual-encoder training loss is beneficial for knowledge transfer. Based on these findings we propose a novel Contrastive Partial Ranking Distillation (CPRD) method which implements the objective of mimicking relative order between hard negative samples with contrastive learning. This approach coordinates with the training of the dual-encoder effectively transferring valid knowledge from the cross-encoder to the dual-encoder. Extensive experiments on image-text retrieval and ranking tasks show that our method surpasses other distillation methods and significantly improves the accuracy of dual-encoder.

ADR-BC: Adversarial Density Weighted Regression Behavior Cloning

Typically, traditional Imitation Learning (IL) methods first shape a reward or Q function and then use this shaped function within a reinforcement learning (RL) framework to optimize the empirical policy. However, if the shaped reward/Q function does not adequately represent the ground truth reward/Q function, updating the policy within a multi-step RL framework may result in cumulative bias, further impacting policy learning. Although utilizing behavior cloning (BC) to learn a policy by directly mimicking a few demonstrations in a single-step updating manner can avoid cumulative bias, BC tends to greedily imitate demonstrated actions, limiting its capacity to generalize to unseen state action pairs. To address these challenges, we propose ADR-BC, which aims to enhance behavior cloning through augmented density-based action support, optimizing the policy with this augmented support. Specifically, the objective of ADR-BC shares the similar physical meanings that matching expert distribution while diverging the sub-optimal distribution. Therefore, ADR-BC can achieve more robust expert distribution matching. Meanwhile, as a one-step behavior cloning framework, ADR-BC avoids the cumulative bias associated with multi-step RL frameworks. To validate the performance of ADR-BC, we conduct extensive experiments. Specifically, ADR-BC showcases a 10.5% improvement over the previous state-of-the-art (SOTA) generalized IL baseline, CEIL, across all tasks in the Gym-Mujoco domain. Additionally, it achieves an 89.5% improvement over Implicit Q Learning (IQL) using real rewards across all tasks in the Adroit and Kitchen domains. On the other hand, we conduct extensive ablations to further demonstrate the effectiveness of ADR-BC.

Reinformer: Max-Return Sequence Modeling for offline RL

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks the core objective of RL that maximizes the return. This overlook directly leads to the lack of trajectory stitching capability that affects the sequence model learning from sub-optimal data. In this work, we introduce the concept of max-return sequence modeling which integrates the goal of maximizing returns into existing sequence models. We propose Reinforced Transformer (Reinformer), indicating the sequence model is reinforced by the RL objective. Reinformer additionally incorporates the objective of maximizing returns in the training phase, aiming to predict the maximum future return within the distribution. During inference, this in-distribution maximum return will guide the selection of optimal actions. Empirically, Reinformer is competitive with classical RL methods on the D4RL benchmark and outperforms state-of-the-art sequence model particularly in trajectory stitching ability. Code is public at \url{https://github.com/Dragon-Zhuang/Reinformer}.

Towards Scalability and Extensibility of Query Reformulation Modeling in E-commerce Search

Customer behavioral data significantly impacts e-commerce search systems. However, in the case of less common queries, the associated behavioral data tends to be sparse and noisy, offering inadequate support to the search mechanism. To address this challenge, the concept of query reformulation has been introduced. It suggests that less common queries could utilize the behavior patterns of their popular counterparts with similar meanings. In Amazon product search, query reformulation has displayed its effectiveness in improving search relevance and bolstering overall revenue. Nonetheless, adapting this method for smaller or emerging businesses operating in regions with lower traffic and complex multilingual settings poses the challenge in terms of scalability and extensibility. This study focuses on overcoming this challenge by constructing a query reformulation solution capable of functioning effectively, even when faced with limited training data, in terms of quality and scale, along with relatively complex linguistic characteristics. In this paper we provide an overview of the solution implemented within Amazon product search infrastructure, which encompasses a range of elements, including refining the data mining process, redefining model training objectives, and reshaping training strategies. The effectiveness of the proposed solution is validated through online A/B testing on search ranking and Ads matching. Notably, employing the proposed solution in search ranking resulted in 0.14% and 0.29% increase in overall revenue in Japanese and Hindi cases, respectively, and a 0.08\% incremental gain in the English case compared to the legacy implementation; while in search Ads matching led to a 0.36% increase in Ads revenue in the Japanese case.

Context-Former: Stitching via Latent Conditioned Sequence Modeling

Offline reinforcement learning (RL) algorithms can improve the decision making via stitching sub-optimal trajectories to obtain more optimal ones. This capability is a crucial factor in enabling RL to learn policies that are superior to the behavioral policy. On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance. In order to endow stitching capability to DT, we abstract trajectory stitching as expert matching and introduce our approach, ContextFormer, which integrates contextual information-based imitation learning (IL) and sequence modeling to stitch sub-optimal trajectory fragments by emulating the representations of a limited number of expert trajectories. To validate our claim, we conduct experiments from two perspectives: 1) We conduct extensive experiments on D4RL benchmarks under the settings of IL, and experimental results demonstrate ContextFormer can achieve competitive performance in multi-IL settings. 2) More importantly, we conduct a comparison of ContextFormer with diverse competitive DT variants using identical training datasets. The experimental results unveiled ContextFormer's superiority, as it outperformed all other variants, showcasing its remarkable performance.

Set Prediction Guided by Semantic Concepts for Diverse Video Captioning

Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergistic tasks, i.e., caption generation and an auxiliary task of concept combination prediction providing extra semantic supervision. Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction. Furthermore, we apply a diversity regularization term on concepts to encourage the model to generate semantically diverse captions with various concept combinations. These two tasks share multiple semantics-specific encodings as input, which are obtained by iterative interaction between visual features and conceptual queries. The correspondence between the generated captions and specific concept combinations further guarantees the interpretability of our model. Extensive experiments on benchmark datasets show that the proposed SCG-SP achieves state-of-the-art (SOTA) performance under both relevance and diversity metrics.

Adaptive Proximal Policy Optimization with Upper Confidence Bound

Trust Region Policy Optimization (TRPO) attractively optimizes the policy while constraining the update of the new policy within a trust region, ensuring the stability and monotonic optimization. Building on the theoretical guarantees of trust region optimization, Proximal Policy Optimization (PPO) successfully enhances the algorithm's sample efficiency and reduces deployment complexity by confining the update of the new and old policies within a surrogate trust region. However, this approach is limited by the fixed setting of surrogate trust region and is not sufficiently adaptive, because there is no theoretical proof that the optimal clipping bound remains consistent throughout the entire training process, truncating the ratio of the new and old policies within surrogate trust region can ensure that the algorithm achieves its best performance, therefore, exploring and researching a dynamic clip bound for improving PPO's performance can be quite beneficial. To design an adaptive clipped trust region and explore the dynamic clip bound's impact on the performance of PPO, we introduce an adaptive PPO-CLIP (Adaptive-PPO) method that dynamically explores and exploits the clip bound using a bandit during the online training process. Furthermore, ample experiments will initially demonstrate that our Adaptive-PPO exhibits sample efficiency and performance compared to PPO-CLIP.