Painterly Image Harmonization aims at seamlessly blending disparate visual elements within a single coherent image. However, previous approaches often encounter significant limitations due to training data constraints, the need for time-consuming fine-tuning, or reliance on additional prompts. To surmount these hurdles, we design a Training-and-prompt-Free General Painterly Harmonization method using image-wise attention sharing (TF-GPH), which integrates a novel "share-attention module". This module redefines the traditional self-attention mechanism by allowing for comprehensive image-wise attention, facilitating the use of a state-of-the-art pretrained latent diffusion model without the typical training data limitations. Additionally, we further introduce "similarity reweighting" mechanism enhances performance by effectively harnessing cross-image information, surpassing the capabilities of fine-tuning or prompt-based approaches. At last, we recognize the deficiencies in existing benchmarks and propose the "General Painterly Harmonization Benchmark", which employs range-based evaluation metrics to more accurately reflect real-world application. Extensive experiments demonstrate the superior efficacy of our method across various benchmarks. The code and web demo are available at https://github.com/BlueDyee/TF-GPH.
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.
Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects, whose scale is extraordinarily smaller than general objects. Also, DETR-like methods using a fixed number of queries make them unsuitable for aerial datasets, which only contain tiny objects, and the numbers of instances are imbalanced between different images. Thus, we present a simple yet effective model, named DQ-DETR, which consists of three different components: categorical counting module, counting-guided feature enhancement, and dynamic query selection to solve the above-mentioned problems. DQ-DETR uses the prediction and density maps from the categorical counting module to dynamically adjust the number of object queries and improve the positional information of queries. Our model DQ-DETR outperforms previous CNN-based and DETR-like methods, achieving state-of-the-art mAP 30.2% on the AI-TOD-V2 dataset, which mostly consists of tiny objects.
Monocular 3D object detection (Mono3D) is an indispensable research topic in autonomous driving, thanks to the cost-effective monocular camera sensors and its wide range of applications. Since the image perspective has depth ambiguity, the challenges of Mono3D lie in understanding 3D scene geometry and reconstructing 3D object information from a single image. Previous methods attempted to transfer 3D information directly from the LiDAR-based teacher to the camera-based student. However, a considerable gap in feature representation makes direct cross-modal distillation inefficient, resulting in a significant performance deterioration between the LiDAR-based teacher and the camera-based student. To address this issue, we propose the Teaching Assistant Knowledge Distillation (MonoTAKD) to break down the learning objective by integrating intra-modal distillation with cross-modal residual distillation. In particular, we employ a strong camera-based teaching assistant model to distill powerful visual knowledge effectively through intra-modal distillation. Subsequently, we introduce the cross-modal residual distillation to transfer the 3D spatial cues. By acquiring both visual knowledge and 3D spatial cues, the predictions of our approach are rigorously evaluated on the KITTI 3D object detection benchmark and achieve state-of-the-art performance in Mono3D.
We present TMMLU+, a comprehensive dataset designed for the Traditional Chinese massive multitask language understanding dataset. TMMLU+ is a multiple-choice question-answering dataset with 66 subjects from elementary to professional level. Compared to its predecessor, TMMLU, TMMLU+ is six times larger and boasts a more balanced subject distribution. We included benchmark results in TMMLU+ from closed-source models and 24 open-weight Chinese large language models of parameters ranging from 1.8B to 72B. Our findings reveal that Traditional Chinese models still trail behind their Simplified Chinese counterparts. Additionally, current large language models have yet to outperform human performance in average scores. We publicly release our dataset and the corresponding benchmark source code.
Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this ability in the vision-language domain by incorporating visual information into large language models that can already make in-context predictions. However, these methods could inherit issues in the language domain, such as template sensitivity and hallucination. Also, the scale of these language models raises a significant demand for computations, making learning and operating these models resource-intensive. To this end, we raise a question: ``How can we enable in-context learning for general models without being constrained on large language models?". To answer it, we propose a succinct and general framework, Self-supervised IN-Context learning (SINC), that introduces a meta-model to learn on self-supervised prompts consisting of tailored demonstrations. The learned models can be transferred to downstream tasks for making in-context predictions on-the-fly. Extensive experiments show that SINC outperforms gradient-based methods in various vision-language tasks under few-shot settings. Furthermore, the designs of SINC help us investigate the benefits of in-context learning across different tasks, and the analysis further reveals the essential components for the emergence of in-context learning in the vision-language domain.
Review-Based Recommender Systems (RBRS) have attracted increasing research interest due to their ability to alleviate well-known cold-start problems. RBRS utilizes reviews to construct the user and items representations. However, in this paper, we argue that such a reliance on reviews may instead expose systems to the risk of being shilled. To explore this possibility, in this paper, we propose the first generation-based model for shilling attacks against RBRSs. Specifically, we learn a fake review generator through reinforcement learning, which maliciously promotes items by forcing prediction shifts after adding generated reviews to the system. By introducing the auxiliary rewards to increase text fluency and diversity with the aid of pre-trained language models and aspect predictors, the generated reviews can be effective for shilling with high fidelity. Experimental results demonstrate that the proposed framework can successfully attack three different kinds of RBRSs on the Amazon corpus with three domains and Yelp corpus. Furthermore, human studies also show that the generated reviews are fluent and informative. Finally, equipped with Attack Review Generators (ARGs), RBRSs with adversarial training are much more robust to malicious reviews.
Neural abstractive summarization has been widely studied and achieved great success with large-scale corpora. However, the considerable cost of annotating data motivates the need for learning strategies under low-resource settings. In this paper, we investigate the problems of learning summarizers with only few examples and propose corresponding methods for improvements. First, typical transfer learning methods are prone to be affected by data properties and learning objectives in the pretext tasks. Therefore, based on pretrained language models, we further present a meta learning framework to transfer few-shot learning processes from source corpora to the target corpus. Second, previous methods learn from training examples without decomposing the content and preference. The generated summaries could therefore be constrained by the preference bias in the training set, especially under low-resource settings. As such, we propose decomposing the contents and preferences during learning through the parameter modulation, which enables control over preferences during inference. Third, given a target application, specifying required preferences could be non-trivial because the preferences may be difficult to derive through observations. Therefore, we propose a novel decoding method to automatically estimate suitable preferences and generate corresponding summary candidates from the few training examples. Extensive experiments demonstrate that our methods achieve state-of-the-art performance on six diverse corpora with 30.11%/33.95%/27.51% and 26.74%/31.14%/24.48% average improvements on ROUGE-1/2/L under 10- and 100-example settings.
Group affect refers to the subjective emotion that is evoked by an external stimulus in a group, which is an important factor that shapes group behavior and outcomes. Recognizing group affect involves identifying important individuals and salient objects among a crowd that can evoke emotions. Most of the existing methods are proposed to detect faces and objects using pre-trained detectors and summarize the results into group emotions by specific rules. However, such affective region selection mechanisms are heuristic and susceptible to imperfect faces and objects from the pre-trained detectors. Moreover, faces and objects on group-level images are often contextually relevant. There is still an open question about how important faces and objects can be interacted with. In this work, we incorporate the psychological concept called Most Important Person (MIP). It represents the most noteworthy face in the crowd and has an affective semantic meaning. We propose the Dual-branch Cross-Patch Attention Transformer (DCAT) which uses global image and MIP together as inputs. Specifically, we first learn the informative facial regions produced by the MIP and the global context separately. Then, the Cross-Patch Attention module is proposed to fuse the features of MIP and global context together to complement each other. With parameters less than 10x, the proposed DCAT outperforms state-of-the-art methods on two datasets of group valence prediction, GAF 3.0 and GroupEmoW datasets. Moreover, our proposed model can be transferred to another group affect task, group cohesion, and shows comparable results.