Jin Ma

Jinlong Li, Runsheng Xu, Xinyu Liu et al.

Deep learning has been widely used in the perception (e.g., 3D object detection) of intelligent vehicle driving. Due to the beneficial Vehicle-to-Vehicle (V2V) communication, the deep learning based features from other agents can be shared to the ego vehicle so as to improve the perception of the ego vehicle. It is named as Cooperative Perception in the V2V research, whose algorithms have been dramatically advanced recently. However, all the existing cooperative perception algorithms assume the ideal V2V communication without considering the possible lossy shared features because of the Lossy Communication (LC) which is common in the complex real-world driving scenarios. In this paper, we first study the side effect (e.g., detection performance drop) by the lossy communication in the V2V Cooperative Perception, and then we propose a novel intermediate LC-aware feature fusion method to relieve the side effect of lossy communication by a LC-aware Repair Network (LCRN) and enhance the interaction between the ego vehicle and other vehicles by a specially designed V2V Attention Module (V2VAM) including intra-vehicle attention of ego vehicle and uncertainty-aware inter-vehicle attention. The extensive experiment on the public cooperative perception dataset OPV2V (based on digital-twin CARLA simulator) demonstrates that the proposed method is quite effective for the cooperative point cloud based 3D object detection under lossy V2V communication.

Yizhen Chen, Jie Wang, Lijian Lin et al.

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.

Haibin Yu, Yuxuan Hu, Yao Qian et al.

Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T), in Mandarin-English code-switching speech recognition. We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models, i.e., 16% relative Token-based Error Rate (TER) reduction averaged on three evaluation sets, and the approach of tying speech and text latent spaces is superior to that of TTS conversion on the evaluation set which contains more homogeneous data with the training set.

Songyang Gao, Shihan Dou, Qi Zhang et al.

Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications. However, existing adversarial detection methods require access to sufficient training data, which brings noteworthy concerns regarding privacy leakage and generalizability. In this work, we validate that the adversarial sample generated by attack algorithms is strongly related to a specific vector in the high-dimensional inputs. Such vectors, namely UAPs (Universal Adversarial Perturbations), can be calculated without original training data. Based on this discovery, we propose a data-agnostic adversarial detection framework, which induces different responses between normal and adversarial samples to UAPs. Experimental results show that our method achieves competitive detection performance on various text classification tasks, and maintains an equivalent time consumption to normal inference.

Xinyu Liu, Jinlong Li, Jin Ma et al.

Deep learning-based intelligent vehicle perception has been developing prominently in recent years to provide a reliable source for motion planning and decision making in autonomous driving. A large number of powerful deep learning-based methods can achieve excellent performance in solving various perception problems of autonomous driving. However, these deep learning methods still have several limitations, for example, the assumption that lab-training (source domain) and real-testing (target domain) data follow the same feature distribution may not be practical in the real world. There is often a dramatic domain gap between them in many real-world cases. As a solution to this challenge, deep transfer learning can handle situations excellently by transferring the knowledge from one domain to another. Deep transfer learning aims to improve task performance in a new domain by leveraging the knowledge of similar tasks learned in another domain before. Nevertheless, there are currently no survey papers on the topic of deep transfer learning for intelligent vehicle perception. To the best of our knowledge, this paper represents the first comprehensive survey on the topic of the deep transfer learning for intelligent vehicle perception. This paper discusses the domain gaps related to the differences of sensor, data, and model for the intelligent vehicle perception. The recent applications, challenges, future researches in intelligent vehicle perception are also explored.

Jinlong Li, Runsheng Xu, Xinyu Liu et al.

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, this such assumption may fail in different weather conditions. Due to the domain gap, a detection model trained under clear weather may not perform well in foggy and rainy conditions. Overcoming detection bottlenecks in foggy and rainy weather is a real challenge for autonomous vehicles deployed in the wild. To bridge the domain gap and improve the performance of object detection in foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection. The adaptations at both the image-level and object-level are intended to minimize the differences in image style and object appearance between domains. Furthermore, in order to improve the model's performance on challenging examples, we introduce a novel adversarial gradient reversal layer that conducts adversarial mining on difficult instances in addition to domain adaptation. Additionally, we suggest generating an auxiliary domain through data augmentation to enforce a new domain-level metric regularization. Experimental findings on public benchmark exhibit a substantial enhancement in object detection specifically for foggy and rainy driving scenarios.

Huiming Sun, Jin Ma, Qing Guo et al.

The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases, the geoscience images might contain occlusions during the image acquisition. This problem actually implies the image inpainting problem in computer vision and multimedia. To the best of our knowledge, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but not good enough for geoscience images by ignoring the geoscience related tasks. This paper aims to repair the occluded regions for a better geoscience task performance with the advanced visualization quality simultaneously, without changing the current deployed deep learning based geoscience models. Because of the complex context of geoscience images, we propose a coarse-to-fine encoder-decoder network with coarse-to-fine adversarial context discriminators to reconstruct the occluded image regions. Due to the limited data of geoscience images, we use a MaskMix based data augmentation method to exploit more information from limited geoscience image data. The experimental results on three public geoscience datasets for remote sensing scene recognition, cross-view geolocation and semantic segmentation tasks respectively show the effectiveness and accuracy of the proposed method.

Songyang Gao, Shihan Dou, Yan Liu et al.

Adversarial training is one of the best-performing methods in improving the robustness of deep language models. However, robust models come at the cost of high time consumption, as they require multi-step gradient ascents or word substitutions to obtain adversarial samples. In addition, these generated samples are deficient in grammatical quality and semantic consistency, which impairs the effectiveness of adversarial training. To address these problems, we introduce a novel, effective procedure for instead adversarial training with only clean data. Our procedure, distribution shift risk minimization (DSRM), estimates the adversarial loss by perturbing the input data's probability distribution rather than their embeddings. This formulation results in a robust model that minimizes the expected global loss under adversarial attacks. Our approach requires zero adversarial samples for training and reduces time consumption by up to 70\% compared to current best-performing adversarial training methods. Experiments demonstrate that DSRM considerably improves BERT's resistance to textual adversarial attacks and achieves state-of-the-art robust accuracy on various benchmarks.

Jin Ma, Jinlong Li, Qing Guo et al.

The emergence of different sensors (Near-Infrared, Depth, etc.) is a remedy for the limited application scenarios of traditional RGB camera. The RGB-X tasks, which rely on RGB input and another type of data input to resolve specific problems, have become a popular research topic in multimedia. A crucial part in two-branch RGB-X deep neural networks is how to fuse information across modalities. Given the tremendous information inside RGB-X networks, previous works typically apply naive fusion (e.g., average or max fusion) or only focus on the feature fusion at the same scale(s). While in this paper, we propose a novel method called RXFOOD for the fusion of features across different scales within the same modality branch and from different modality branches simultaneously in a unified attention mechanism. An Energy Exchange Module is designed for the interaction of each feature map's energy matrix, who reflects the inter-relationship of different positions and different channels inside a feature map. The RXFOOD method can be easily incorporated to any dual-branch encoder-decoder network as a plug-in module, and help the original backbone network better focus on important positions and channels for object of interest detection. Experimental results on RGB-NIR salient object detection, RGB-D salient object detection, and RGBFrequency image manipulation detection demonstrate the clear effectiveness of the proposed RXFOOD.

Bingning Wang, Feiyang Lv, Ting Yao et al.

Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the given image, such as `What color are her eyes?'. The human generated crowdsourcing questions are relatively simple and sometimes have the bias toward certain entities or attributes. In this paper, we introduce a new question answering dataset based on image-ChiQA. It contains the real-world queries issued by internet users, combined with several related open-domain images. The system should determine whether the image could answer the question or not. Different from previous VQA datasets, the questions are real-world image-independent queries that are more various and unbiased. Compared with previous image-retrieval or image-caption datasets, the ChiQA not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. ChiQA contains more than 40K questions and more than 200K question-images pairs. A three-level 2/1/0 label is assigned to each pair indicating perfect answer, partially answer and irrelevant. Data analysis shows ChiQA requires a deep understanding of both language and vision, including grounding, comparisons, and reading. We evaluate several state-of-the-art visual-language models such as ALBEF, demonstrating that there is still a large room for improvements on ChiQA.

Dezhi Ye, Junwei Hu, Jiabin Fan et al.

Recent studies have highlighted the significant potential of Large Language Models (LLMs) as zero-shot relevance rankers. These methods predominantly utilize prompt learning to assess the relevance between queries and documents by generating a ranked list of potential documents. Despite their promise, the substantial costs associated with LLMs pose a significant challenge for their direct implementation in commercial search systems. To overcome this barrier and fully exploit the capabilities of LLMs for text ranking, we explore techniques to transfer the ranking expertise of LLMs to a more compact model similar to BERT, using a ranking loss to enable the deployment of less resource-intensive models. Specifically, we enhance the training of LLMs through Continued Pre-Training, taking the query as input and the clicked title and summary as output. We then proceed with supervised fine-tuning of the LLM using a rank loss, assigning the final token as a representative of the entire sentence. Given the inherent characteristics of autoregressive language models, only the final token </s> can encapsulate all preceding tokens. Additionally, we introduce a hybrid point-wise and margin MSE loss to transfer the ranking knowledge from LLMs to smaller models like BERT. This method creates a viable solution for environments with strict resource constraints. Both offline and online evaluations have confirmed the efficacy of our approach, and our model has been successfully integrated into a commercial web search engine as of February 2024.

Limao Xiong, Jie Zhou, Qunxi Zhu et al.

Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets, which always obtain using crowdsourcing. However, it is hard to obtain a unified and correct label via majority voting from multiple annotators for NER due to the large labeling space and complexity of this task. To address this problem, we aim to utilize the original multi-annotator labels directly. Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER. This model learns a token- and content-dependent confidence via an Expectation-Maximization (EM) algorithm by minimizing empirical risk. The true posterior estimator and confidence estimator perform iteratively to update the true posterior and confidence respectively. We conduct extensive experimental results on both real-world and synthetic datasets, which show that our model can improve performance effectively compared with strong baselines.