Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples

Existing Vision-Language Pretraining (VLP) methods have achieved remarkable improvements across a variety of vision-language tasks, confirming their effectiveness in capturing coarse-grained semantic correlations. However, their capability for fine-grained understanding, which is critical for many nuanced vision-language applications, remains limited. Prevailing VLP models often overlook the intricate distinctions in expressing different modal features and typically depend on the similarity of holistic features for cross-modal interactions. Moreover, these models directly align and integrate features from different modalities, focusing more on coarse-grained general representations, thus failing to capture the nuanced differences necessary for tasks demanding a more detailed perception. In response to these limitations, we introduce Negative Augmented Samples(NAS), a refined vision-language pretraining model that innovatively incorporates NAS to specifically address the challenge of fine-grained understanding. NAS utilizes a Visual Dictionary(VD) as a semantic bridge between visual and linguistic domains. Additionally, it employs a Negative Visual Augmentation(NVA) method based on the VD to generate challenging negative image samples. These samples deviate from positive samples exclusively at the token level, thereby necessitating that the model discerns the subtle disparities between positive and negative samples with greater precision. Comprehensive experiments validate the efficacy of NAS components and underscore its potential to enhance fine-grained vision-language comprehension.

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators

Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM has shown SOTA performance on reference-free evaluation, the predicted errors do not align well with those annotated by human, limiting their interpretability as feedback signals. To enhance the quality of error annotations predicted by LLM evaluators, we introduce a universal and training-free framework, $\textbf{MQM-APE}$, based on the idea of filtering out non-impactful errors by Automatically Post-Editing (APE) the original translation based on each error, leaving only those errors that contribute to quality improvement. Specifically, we prompt the LLM to act as 1) $\textit{evaluator}$ to provide error annotations, 2) $\textit{post-editor}$ to determine whether errors impact quality improvement and 3) $\textit{pairwise quality verifier}$ as the error filter. Experiments show that our approach consistently improves both the reliability and quality of error spans against GEMBA-MQM, across eight LLMs in both high- and low-resource languages. Orthogonal to trained approaches, MQM-APE complements translation-specific evaluators such as Tower, highlighting its broad applicability. Further analysis confirm the effectiveness of each module and offer valuable insights into evaluator design and LLMs selection. The code will be released to facilitate the community.

Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

Efficient and accurate camouflaged object detection (COD) poses a challenge in the field of computer vision. Recent approaches explored the utility of edge information for network co-supervision, achieving notable advancements. However, these approaches introduce an extra branch for complex edge extraction, complicate the model architecture and increases computational demands. Addressing this issue, our work replicates the effect that animal's camouflage can be easily revealed under a shifting spotlight, and leverages it for network co-supervision to form a compact yet efficient single-branch network, the Co-Supervised Spotlight Shifting Network (CS$^3$Net). The spotlight shifting strategy allows CS$^3$Net to learn additional prior within a single-branch framework, obviating the need for resource demanding multi-branch design. To leverage the prior of spotlight shifting co-supervision, we propose Shadow Refinement Module (SRM) and Projection Aware Attention (PAA) for feature refinement and enhancement. To ensure the continuity of multi-scale features aggregation, we utilize the Extended Neighbor Connection Decoder (ENCD) for generating the final predictions. Empirical evaluations on public datasets confirm that our CS$^3$Net offers an optimal balance between efficiency and performance: it accomplishes a 32.13% reduction in Multiply-Accumulate (MACs) operations compared to leading efficient COD models, while also delivering superior performance.

A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation

Nowadays, the rapid development of photovoltaic(PV) power stations requires increasingly reliable maintenance and fault diagnosis of PV modules in the field. Due to the effectiveness, convolutional neural network (CNN) has been widely used in the existing automatic defect detection of PV cells. However, the parameters of these CNN-based models are very large, which require stringent hardware resources and it is difficult to be applied in actual industrial projects. To solve these problems, we propose a novel lightweight high-performance model for automatic defect detection of PV cells in electroluminescence(EL) images based on neural architecture search and knowledge distillation. To auto-design an effective lightweight model, we introduce neural architecture search to the field of PV cell defect classification for the first time. Since the defect can be any size, we design a proper search structure of network to better exploit the multi-scale characteristic. To improve the overall performance of the searched lightweight model, we further transfer the knowledge learned by the existing pre-trained large-scale model based on knowledge distillation. Different kinds of knowledge are exploited and transferred, including attention information, feature information, logit information and task-oriented information. Experiments have demonstrated that the proposed model achieves the state-of-the-art performance on the public PV cell dataset of EL images under online data augmentation with accuracy of 91.74% and the parameters of 1.85M. The proposed lightweight high-performance model can be easily deployed to the end devices of the actual industrial projects and retain the accuracy.