Abstract:Many targets are often very small in infrared images due to the long-distance imaging meachnism. UNet and its variants, as popular detection backbone networks, downsample the local features early and cause the irreversible loss of these local features, leading to both the missed and false detection of small targets in infrared images. We propose HintU, a novel network to recover the local features lost by various UNet-based methods for effective infrared small target detection. HintU has two key contributions. First, it introduces the "Hint" mechanism for the first time, i.e., leveraging the prior knowledge of target locations to highlight critical local features. Second, it improves the mainstream UNet-based architecture to preserve target pixels even after downsampling. HintU can shift the focus of various networks (e.g., vanilla UNet, UNet++, UIUNet, MiM+, and HCFNet) from the irrelevant background pixels to a more restricted area from the beginning. Experimental results on three datasets NUDT-SIRST, SIRSTv2 and IRSTD1K demonstrate that HintU enhances the performance of existing methods with only an additional 1.88 ms cost (on RTX Titan). Additionally, the explicit constraints of HintU enhance the generalization ability of UNet-based methods. Code is available at https://github.com/Wuzhou-Quan/HintU.
Abstract:Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image personalization: Textual Inversion and DreamBooth. When integrating the learned concept into new prompts, Textual Inversion tends to overfit the concept, while DreamBooth often overlooks it. We attribute these issues to the incorrect learning of the embedding alignment for the concept. We introduce AttnDreamBooth, a novel approach that addresses these issues by separately learning the embedding alignment, the attention map, and the subject identity in different training stages. We also introduce a cross-attention map regularization term to enhance the learning of the attention map. Our method demonstrates significant improvements in identity preservation and text alignment compared to the baseline methods.
Abstract:Adverse weather conditions often impair the quality of captured images, inevitably inducing cutting-edge object detection models for advanced driver assistance systems (ADAS) and autonomous driving. In this paper, we raise an intriguing question: can the combination of image restoration and object detection enhance detection performance in adverse weather conditions? To answer it, we propose an effective architecture that bridges image dehazing and object detection together via guidance information and task-driven learning to achieve detection-friendly dehazing, termed FriendNet. FriendNet aims to deliver both high-quality perception and high detection capacity. Different from existing efforts that intuitively treat image dehazing as pre-processing, FriendNet establishes a positive correlation between these two tasks. Clean features generated by the dehazing network potentially contribute to improvements in object detection performance. Conversely, object detection crucially guides the learning process of the image dehazing network under the task-driven learning scheme. We shed light on how downstream tasks can guide upstream dehazing processes, considering both network architecture and learning objectives. We design Guidance Fusion Block (GFB) and Guidance Attention Block (GAB) to facilitate the integration of detection information into the network. Furthermore, the incorporation of the detection task loss aids in refining the optimization process. Additionally, we introduce a new Physics-aware Feature Enhancement Block (PFEB), which integrates physics-based priors to enhance the feature extraction and representation capabilities. Extensive experiments on synthetic and real-world datasets demonstrate the superiority of our method over state-of-the-art methods on both image quality and detection precision. Our source code is available at https://github.com/fanyihua0309/FriendNet.
Abstract:With the continuous growth in the number of parameters of transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of parameters, many natural language processing (NLP) tasks have demonstrated remarkable success. However, the enormous size and computational demands of these models pose significant challenges for adapting them to specific downstream tasks, especially in environments with limited computational resources. Parameter Efficient Fine-Tuning (PEFT) offers an effective solution by reducing the number of fine-tuning parameters and memory usage while achieving comparable performance to full fine-tuning. The demands for fine-tuning PLMs, especially LLMs, have led to a surge in the development of PEFT methods, as depicted in Fig. 1. In this paper, we present a comprehensive and systematic review of PEFT methods for PLMs. We summarize these PEFT methods, discuss their applications, and outline future directions. Furthermore, we conduct experiments using several representative PEFT methods to better understand their effectiveness in parameter efficiency and memory efficiency. By offering insights into the latest advancements and practical applications, this survey serves as an invaluable resource for researchers and practitioners seeking to navigate the challenges and opportunities presented by PEFT in the context of PLMs.
Abstract:Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different modalities. In this paper, we address these challenges by exploring the implicit semantic and geometric correlations between 2D and 3D data of the same objects/scenes. We propose a new cross-modal BERT-style self-supervised learning paradigm, called Cross-BERT. To facilitate pretraining for irregular and sparse point clouds, we design two self-supervised tasks to boost cross-modal interaction. The first task, referred to as Point-Image Alignment, aims to align features between unimodal and cross-modal representations to capture the correspondences between the 2D and 3D modalities. The second task, termed Masked Cross-modal Modeling, further improves mask modeling of BERT by incorporating high-dimensional semantic information obtained by cross-modal interaction. By performing cross-modal interaction, Cross-BERT can smoothly reconstruct the masked tokens during pretraining, leading to notable performance enhancements for downstream tasks. Through empirical evaluation, we demonstrate that Cross-BERT outperforms existing state-of-the-art methods in 3D downstream applications. Our work highlights the effectiveness of leveraging cross-modal 2D knowledge to strengthen 3D point cloud representation and the transferable capability of BERT across modalities.
Abstract:Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to divide long documents into chunks and stack a self-attention backbone with the recurrent structure to extract semantic representation. Such an approach disables parallelization of the attention mechanism, significantly increasing the training cost and raising hardware requirements. Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention. Combining the advantages from both sides, the well-designed RAN is capable of extracting global semantics in both token-level and document-level representations, making it inherently compatible with both sequential and classification tasks, respectively. Furthermore, RAN is computationally scalable as it supports parallelization on long document processing. Extensive experiments demonstrate the long-text encoding ability of the proposed RAN model on both classification and sequential tasks, showing its potential for a wide range of applications.
Abstract:Searching by image is popular yet still challenging due to the extensive interference arose from i) data variations (e.g., background, pose, visual angle, brightness) of real-world captured images and ii) similar images in the query dataset. This paper studies a practically meaningful problem of beauty product retrieval (BPR) by neural networks. We broadly extract different types of image features, and raise an intriguing question that whether these features are beneficial to i) suppress data variations of real-world captured images, and ii) distinguish one image from others which look very similar but are intrinsically different beauty products in the dataset, therefore leading to an enhanced capability of BPR. To answer it, we present a novel variable-attention neural network to understand the combination of multiple features (termed VM-Net) of beauty product images. Considering that there are few publicly released training datasets for BPR, we establish a new dataset with more than one million images classified into more than 20K categories to improve both the generalization and anti-interference abilities of VM-Net and other methods. We verify the performance of VM-Net and its competitors on the benchmark dataset Perfect-500K, where VM-Net shows clear improvements over the competitors in terms of MAP@7. The source code and dataset will be released upon publication.
Abstract:What will happen when unsupervised learning meets diffusion models for real-world image deraining? To answer it, we propose RainDiffusion, the first unsupervised image deraining paradigm based on diffusion models. Beyond the traditional unsupervised wisdom of image deraining, RainDiffusion introduces stable training of unpaired real-world data instead of weakly adversarial training. RainDiffusion consists of two cooperative branches: Non-diffusive Translation Branch (NTB) and Diffusive Translation Branch (DTB). NTB exploits a cycle-consistent architecture to bypass the difficulty in unpaired training of standard diffusion models by generating initial clean/rainy image pairs. DTB leverages two conditional diffusion modules to progressively refine the desired output with initial image pairs and diffusive generative prior, to obtain a better generalization ability of deraining and rain generation. Rain-Diffusion is a non adversarial training paradigm, serving as a new standard bar for real-world image deraining. Extensive experiments confirm the superiority of our RainDiffusion over un/semi-supervised methods and show its competitive advantages over fully-supervised ones.
Abstract:There is a trend to fuse multi-modal information for 3D object detection (3OD). However, the challenging problems of low lightweightness, poor flexibility of plug-and-play, and inaccurate alignment of features are still not well-solved, when designing multi-modal fusion newtorks. We propose PointSee, a lightweight, flexible and effective multi-modal fusion solution to facilitate various 3OD networks by semantic feature enhancement of LiDAR point clouds assembled with scene images. Beyond the existing wisdom of 3OD, PointSee consists of a hidden module (HM) and a seen module (SM): HM decorates LiDAR point clouds using 2D image information in an offline fusion manner, leading to minimal or even no adaptations of existing 3OD networks; SM further enriches the LiDAR point clouds by acquiring point-wise representative semantic features, leading to enhanced performance of existing 3OD networks. Besides the new architecture of PointSee, we propose a simple yet efficient training strategy, to ease the potential inaccurate regressions of 2D object detection networks. Extensive experiments on the popular outdoor/indoor benchmarks show numerical improvements of our PointSee over twenty-two state-of-the-arts.
Abstract:We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD). Beyond the traditional wisdom of PCD, to fully exploit the geometric information of point clouds, we define two kinds of surface normals, one is called Real Normal (RN), and the other is Virtual Normal (VN). RN preserves the local details of noisy point clouds while VN avoids the global shape shrinkage during denoising. GeoGCN is a new PCD paradigm that, 1) first regresses point positions by spatialbased GCN with the help of VNs, 2) then estimates initial RNs by performing Principal Component Analysis on the regressed points, and 3) finally regresses fine RNs by normalbased GCN. Unlike existing PCD methods, GeoGCN not only exploits two kinds of geometry expertise (i.e., RN and VN) but also benefits from training data. Experiments validate that GeoGCN outperforms SOTAs in terms of both noise-robustness and local-and-global feature preservation.