Correctness: In Table 1, baseline methods are thresholded at a 95% TPR, while the proposed method and its variants are claimed to be threshold-agnostic: From section 3.3 it appears that the threshold is manually set to be 0.5, so they are not really threshold agnostic. It feels likely to me that there might be situations where picking thresholds with different criteria for comparative methods might lead to an unfair assessment. I'd recommend picking an OOD-detection threshold (on the maximum softmax values for class 1 across all tasks, for example) also at 95% TPR for a more even comparison. The experiment in Section 4.4 feels a bit anecdotal due to the particular example studied. Appendix D studies the effect of the adversarial adaptation, and while the text says random-(ini)-OOD outperforms random-OOD, the table seems to show the opposite trend (a typo perhaps?), which would indicate the adversarial adaptation did not help.

Vision-Language Models (VLMs) are a significant technique for Artificial General Intelligence (AGI). With the fast growth of AGI, the security problem become one of the most important challenges for VLMs. In this paper, through extensive experiments, we demonstrate the vulnerability of the conventional adaptation methods for VLMs, which may bring significant security risks. In addition, as the size of the VLMs increases, performing conventional adversarial adaptation techniques on VLMs results in high computational costs. To solve these problems, we propose a parameter-efficient \underline{Adv}ersarial adaptation method named \underline{AdvLoRA} by \underline{Lo}w-\underline{R}ank \underline{A}daptation. At first, we investigate and reveal the intrinsic low-rank property during the adversarial adaptation for VLMs. Different from LoRA, we improve the efficiency and robustness of adversarial adaptation by designing a novel reparameterizing method based on parameter clustering and parameter alignment. In addition, an adaptive parameter update strategy is proposed to further improve the robustness. By these settings, our proposed AdvLoRA alleviates the model security and high resource waste problems. Extensive experiments demonstrate the effectiveness and efficiency of the AdvLoRA.

Named Entity Recognition (NER) is the task of identifying and classifying named entities in large-scale texts into predefined classes. NER in French and other relatively limited-resource languages cannot always benefit from approaches proposed for languages like English due to a dearth of large, robust datasets. In this paper, we present our work that aims to mitigate the effects of this dearth of large, labeled datasets. We propose a Transformer-based NER approach for French, using adversarial adaptation to similar domain or general corpora to improve feature extraction and enable better generalization. Our approach allows learning better features using large-scale unlabeled corpora from the same domain or mixed domains to introduce more variations during training and reduce overfitting. Experimental results on three labeled datasets show that our adaptation framework outperforms the corresponding non-adaptive models for various combinations of Transformer models, source datasets, and target corpora. We also show that adversarial adaptation to large-scale unlabeled corpora can help mitigate the performance dip incurred on using Transformer models pre-trained on smaller corpora.

Named Entity Recognition (NER) is an information extraction task where specific entities are extracted from unstructured text and labelled into predefined classes. While NER models for high-resource languages like English have seen notable performance gains due to improvements in model architectures and availability of large datasets, limited-resource languages like French still face a dearth of openly available, large, labelled datasets. Recent research works use adversarial adaptation frameworks for adapting NER models from high-resource domains to low-resource domains. These approaches have been used for high-resource languages, where robust language models are available. We utilize adversarial adaptation to enable models to learn better, generalized features by adapting them to large, unlabelled corpora for better performance on source test set. We propose a Transformer-based NER approach for French using adversarial adaptation to counter the lack of large, labelled NER datasets in French. We train transformer-based NER models on labelled source datasets and use larger corpora from similar or mixed domains as target sets for improved feature learning. Our proposed approach helps outsource wider domain and general feature knowledge from easily-available large, unlabelled corpora. While we limit our evaluation to French datasets and corpora, our approach can be applied to other languages too.

Citizen engagement and technology usage are two emerging trends driven by smart city initiatives. Governments around the world are adopting technology for faster resolution of civic issues. Typically, citizens report issues, such as broken roads, garbage dumps, etc. through web portals and mobile apps, in order for the government authorities to take appropriate actions. Several mediums -- text, image, audio, video -- are used to report these issues. Through a user study with 13 citizens and 3 authorities, we found that image is the most preferred medium to report civic issues. However, analyzing civic issue related images is challenging for the authorities as it requires manual effort. Moreover, previous works have been limited to identifying a specific set of issues from images. In this work, given an image, we propose to generate a Civic Issue Graph consisting of a set of objects and the semantic relations between them, which are representative of the underlying civic issue. We also release two multi-modal (text and images) datasets, that can help in further analysis of civic issues from images. We present a novel approach for adversarial training of existing scene graph models that enables the use of scene graphs for new applications in the absence of any labelled training data. We conduct several experiments to analyze the efficacy of our approach, and using human evaluation, we establish the appropriateness of our model at representing different civic issues.