W. F. Mader

Satya Krishna Gorti, Noel Vouitsis, Junwei Ma et al. · gatech, nvidia

In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However, videos inherently express a much wider gamut of information than texts. Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos. Therefore, for a given text, a retrieval model should focus on the text's most semantically similar video sub-regions to make a more relevant comparison. Yet, most existing works aggregate entire videos without directly considering text. Common text-agnostic aggregations schemes include mean-pooling or self-attention over the frames, but these are likely to encode misleading visual information not described in the given text. To address this, we propose a cross-modal attention model called X-Pool that reasons between a text and the frames of a video. Our core mechanism is a scaled dot product attention for a text to attend to its most semantically similar frames. We then generate an aggregated video representation conditioned on the text's attention weights over the frames. We evaluate our method on three benchmark datasets of MSR-VTT, MSVD and LSMDC, achieving new state-of-the-art results by up to 12% in relative improvement in Recall@1. Our findings thereby highlight the importance of joint text-video reasoning to extract important visual cues according to text. Full code and demo can be found at: https://layer6ai-labs.github.io/xpool/

Qiang Hu, Yuejun Guo, Xiaofei Xie et al.

Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data. To alleviate the labeling effort, multiple test selection methods have been proposed where only a subset of test data needs to be labeled while satisfying testing requirements. However, we observe that such methods with reported promising results are only evaluated under simple scenarios, e.g., testing on original test data. This brings a question to us: are they always reliable? In this paper, we explore when and to what extent test selection methods fail for testing. Specifically, first, we identify potential pitfalls of 11 selection methods from top-tier venues based on their construction. Second, we conduct a study on five datasets with two model architectures per dataset to empirically confirm the existence of these pitfalls. Furthermore, we demonstrate how pitfalls can break the reliability of these methods. Concretely, methods for fault detection suffer from test data that are: 1) correctly classified but uncertain, or 2) misclassified but confident. Remarkably, the test relative coverage achieved by such methods drops by up to 86.85%. On the other hand, methods for performance estimation are sensitive to the choice of intermediate-layer output. The effectiveness of such methods can be even worse than random selection when using an inappropriate layer.

Yihong Tang, Haicheng Liao, Tong Nie et al.

End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and human-centric feedback.

Wei Cui, Rasa Hosseinzadeh, Junwei Ma et al.

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed success in image and natural language data, thanks to the domain-specific augmentation techniques that are both intuitive and effective. Nonetheless, in tabular domain, the predominant augmentation technique for creating views is through corrupting tabular entries via swapping values, which is not as sound or effective. We propose a simple yet powerful improvement to this augmentation technique: corrupting tabular data conditioned on class identity. Specifically, when corrupting a specific tabular entry from an anchor row, instead of randomly sampling a value in the same feature column from the entire table uniformly, we only sample from rows that are identified to be within the same class as the anchor row. We assume the semi-supervised learning setting, and adopt the pseudo labeling technique for obtaining class identities over all table rows. We also explore the novel idea of selecting features to be corrupted based on feature correlation structures. Extensive experiments show that the proposed approach consistently outperforms the conventional corruption method for tabular data classification tasks. Our code is available at https://github.com/willtop/Tabular-Class-Conditioned-SSL.

Junjia Huang, Wei Ma, Rong Li et al.

Background: Quantitative prediction of the adolescents' spherical equivalent based on their variable-length historical vision records. Methods: From October 2019 to March 2022, we examined binocular uncorrected visual acuity, axial length, corneal curvature, and axial of 75,172 eyes from 37,586 adolescents aged 6-20 years in Chengdu, China. 80\% samples consist of the training set and the remaining 20\% form the testing set. Time-Aware Long Short-Term Memory was used to quantitatively predict the adolescents' spherical equivalent within two and a half years. Result: The mean absolute prediction error on the testing set was 0.273-0.257 for spherical equivalent, ranging from 0.189-0.160 to 0.596-0.473 if we consider different lengths of historical records and different prediction durations. Conclusions: Time-Aware Long Short-Term Memory was applied to captured the temporal features in irregularly sampled time series, which is more in line with the characteristics of real data and thus has higher applicability, and helps to identify the progression of myopia earlier. The overall error 0.273 is much smaller than the criterion for clinically acceptable prediction, say 0.75.

Junwei Ma, Satya Krishna Gorti, Maksims Volkovs et al.

Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of expensive and error-prone annotation that is required. A common approach is to train a frame-level classifier where frames with the highest class probability are selected to make a video-level prediction. Frame level activations are then used for localization. However, the absence of frame-level annotations cause the classifier to impart class bias on every frame. To address this, we propose the Action Selection Learning (ASL) approach to capture the general concept of action, a property we refer to as "actionness". Under ASL, the model is trained with a novel class-agnostic task to predict which frames will be selected by the classifier. Empirically, we show that ASL outperforms leading baselines on two popular benchmarks THUMOS-14 and ActivityNet-1.2, with 10.3% and 5.7% relative improvement respectively. We further analyze the properties of ASL and demonstrate the importance of actionness. Full code for this work is available here: https://github.com/layer6ai-labs/ASL.

Junlan Chen, Qijie He, Pei Liu et al.

Crash frequency modelling analyzes the impact of factors like traffic volume, road geometry, and environmental conditions on crash occurrences. Inaccurate predictions can distort our understanding of these factors, leading to misguided policies and wasted resources, which jeopardize traffic safety. A key challenge in crash frequency modelling is the prevalence of excessive zero observations, caused by underreporting, the low probability of crashes, and high data collection costs. These zero observations often reduce model accuracy and introduce bias, complicating safety decision making. While existing approaches, such as statistical methods, data aggregation, and resampling, attempt to address this issue, they either rely on restrictive assumptions or result in significant information loss, distorting crash data. To overcome these limitations, we propose a hybrid VAE-Diffusion neural network, designed to reduce zero observations and handle the complexities of multi-type tabular crash data (count, ordinal, nominal, and real-valued variables). We assess the synthetic data quality generated by this model through metrics like similarity, accuracy, diversity, and structural consistency, and compare its predictive performance against traditional statistical models. Our findings demonstrate that the hybrid VAE-Diffusion model outperforms baseline models across all metrics, offering a more effective approach to augmenting crash data and improving the accuracy of crash frequency predictions. This study highlights the potential of synthetic data to enhance traffic safety by improving crash frequency modelling and informing better policy decisions.

Ling Feng, Tianyu Xie, Wei Ma et al.

The modernization of smart farming is a way to improve agricultural production efficiency, and improve the agricultural production environment. Although many large models have achieved high accuracy in the task of object recognition and segmentation, they cannot really be put into use in the farming industry due to their own poor interpretability and limitations in computational volume. In this paper, we built AnYue Shelduck Dateset, which contains a total of 1951 Shelduck datasets, and performed target detection and segmentation annotation with the help of professional annotators. Based on AnYue ShelduckDateset, this paper describes DuckProcessing, an efficient and powerful module for duck identification based on real shelduckfarms. First of all, using the YOLOv8 module designed to divide the mahjong between them, Precision reached 98.10%, Recall reached 96.53% and F1 score reached 0.95 on the test set. Again using the DuckSegmentation segmentation model, DuckSegmentation reached 96.43% mIoU. Finally, the excellent DuckSegmentation was used as the teacher model, and through knowledge distillation, Deeplabv3 r50 was used as the student model, and the final student model achieved 94.49% mIoU on the test set. The method provides a new way of thinking in practical sisal duck smart farming.

Wei Ma, Shangqing Liu, Zhihao Lin et al.

Large language models~(LLMs) demonstrate significant potential to revolutionize software engineering (SE) by exhibiting outstanding performance in SE tasks such as code and document generation. However, the high reliability and risk control requirements in software engineering raise concerns about the lack of interpretability of LLMs. To address this concern, we conducted a study to evaluate the capabilities of LLMs and their limitations for code analysis in SE. We break down the abilities needed for artificial intelligence~(AI) models to address SE tasks related to code analysis into three categories: 1) syntax understanding, 2) static behavior understanding, and 3) dynamic behavior understanding. Our investigation focused on the ability of LLMs to comprehend code syntax and semantic structures, which include abstract syntax trees (AST), control flow graphs (CFG), and call graphs (CG). We employed four state-of-the-art foundational models, GPT4, GPT3.5, StarCoder and CodeLlama-13b-instruct. We assessed the performance of LLMs on cross-language tasks involving C, Java, Python, and Solidity. Our findings revealed that while LLMs have a talent for understanding code syntax, they struggle with comprehending code semantics, particularly dynamic semantics. We conclude that LLMs possess capabilities similar to an Abstract Syntax Tree (AST) parser, demonstrating initial competencies in static code analysis. Furthermore, our study highlights that LLMs are susceptible to hallucinations when interpreting code semantic structures and fabricating nonexistent facts. These results indicate the need to explore methods to verify the correctness of LLM output to ensure its dependability in SE. More importantly, our study provides an initial answer to why the codes generated by LLM are usually syntax-correct but vulnerable.

Jie Zhang, Wei Ma, Qiang Hu et al.

Existing methods for generating adversarial code examples face several challenges: limted availability of substitute variables, high verification costs for these substitutes, and the creation of adversarial samples with noticeable perturbations. To address these concerns, our proposed approach, RNNS, uses a search seed based on historical attacks to find potential adversarial substitutes. Rather than directly using the discrete substitutes, they are mapped to a continuous vector space using a pre-trained variable name encoder. Based on the vector representation, RNNS predicts and selects better substitutes for attacks. We evaluated the performance of RNNS across six coding tasks encompassing three programming languages: Java, Python, and C. We employed three pre-trained code models (CodeBERT, GraphCodeBERT, and CodeT5) that resulted in a cumulative of 18 victim models. The results demonstrate that RNNS outperforms baselines in terms of ASR and QT. Furthermore, the perturbation of adversarial examples introduced by RNNS is smaller compared to the baselines in terms of the number of replaced variables and the change in variable length. Lastly, our experiments indicate that RNNS is efficient in attacking defended models and can be employed for adversarial training.

Qiuyuan Wang, Zike Yan, Junqiu Wang et al.

We propose a visual SLAM method by predicting and updating line flows that represent sequential 2D projections of 3D line segments. While feature-based SLAM methods have achieved excellent results, they still face problems in challenging scenes containing occlusions, blurred images, and repetitive textures. To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3D line along the temporal dimension, which has been neglected in prior SLAM systems. Thanks to this line flow representation, line segments in a new frame can be predicted according to their corresponding 3D lines and their predecessors along the temporal dimension. We create, update, merge, and discard line flows on-the-fly. We model the proposed line flow based SLAM (LF-SLAM) using a Bayesian network. Extensive experimental results demonstrate that the proposed LF-SLAM method achieves state-of-the-art results due to the utilization of line flows. Specifically, LF-SLAM obtains good localization and mapping results in challenging scenes with occlusions, blurred images, and repetitive textures.

Junwei Ma, Satya Krishna Gorti, Maksims Volkovs et al.

We present a novel Cross-Class Relevance Learning approach for the task of temporal concept localization. Most localization architectures rely on feature extraction layers followed by a classification layer which outputs class probabilities for each segment. However, in many real-world applications classes can exhibit complex relationships that are difficult to model with this architecture. In contrast, we propose to incorporate target class and class-related features as input, and learn a pairwise binary model to predict general segment to class relevance. This facilitates learning of shared information between classes, and allows for arbitrary class-specific feature engineering. We apply this approach to the 3rd YouTube-8M Video Understanding Challenge together with other leading models, and achieve first place out of over 280 teams. In this paper we describe our approach and show some empirical results.

Wei Ma, Mike Papadakis, Anestis Tsakmalis et al.

Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can automatically select candidate test data to test deep learning models. Recent research has focused on adapting test selection metrics from code-based software testing (such as coverage) to deep learning. However, deep learning models have different attributes from code such as spread of computations across the entire network reflecting training data properties, balance of neuron weights and redundancy (use of many more neurons than needed). Such differences make code-based metrics inappropriate to select data that can challenge the models (can trigger misclassification). We thus propose a set of test selection metrics based on the notion of model uncertainty (model confidence on specific inputs). Intuitively, the more uncertain we are about a candidate sample, the more likely it is that this sample triggers a misclassification. Similarly, the samples for which we are the most uncertain, are the most informative and should be used to improve the model by retraining. We evaluate these metrics on two widely-used image classification problems involving real and artificial (adversarial) data. We show that uncertainty-based metrics have a strong ability to select data that are misclassified and lead to major improvement in classification accuracy during retraining: up to 80% more gain than random selection and other state-of-the-art metrics on one dataset and up to 29% on the other.

Yuchen Yang, Shuo Liu, Wei Ma et al.

The paper presents a Traffic Sign Recognition (TSR) system, which can fast and accurately recognize traffic signs of different sizes in images. The system consists of two well-designed Convolutional Neural Networks (CNNs), one for region proposals of traffic signs and one for classification of each region. In the proposal CNN, a Fully Convolutional Network (FCN) with a dual multi-scale architecture is proposed to achieve scale invariant detection. In training the proposal network, a modified "Online Hard Example Mining" (OHEM) scheme is adopted to suppress false positives. The classification network fuses multi-scale features as representation and adopts an "Inception" module for efficiency. We evaluate the proposed TSR system and its components with extensive experiments. Our method obtains $99.88\%$ precision and $96.61\%$ recall on the Swedish Traffic Signs Dataset (STSD), higher than state-of-the-art methods. Besides, our system is faster and more lightweight than state-of-the-art deep learning networks for traffic sign recognition.

Jun Lu, Wei Ma, Boi Faltings

It is often the case that the performance of a neural network can be improved by adding layers. In real-world practices, we always train dozens of neural network architectures in parallel which is a wasteful process. We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact. The work of the paper makes two contributions: a). The modified network can converge fast and keep the same functionality so that we do not need to train from scratch again; b). The layer size of the added layer in the neural network is controlled by removing the redundant parameters with sparse optimization. This differs from previous network morphism approaches which tend to add more neurons or channels beyond the actual requirements and result in redundance of the model. The method is illustrated using several neural network structures on different data sets including MNIST and CIFAR10.