Given the inherently costly and time-intensive nature of pixel-level annotation, the generation of synthetic datasets comprising sufficiently diverse synthetic images paired with ground-truth pixel-level annotations has garnered increasing attention recently for training high-performance semantic segmentation models. However, existing methods necessitate to either predict pseudo annotations after image generation or generate images conditioned on manual annotation masks, which incurs image-annotation semantic inconsistency or scalability problem. To migrate both problems with one stone, we present a novel dataset generative diffusion framework for semantic segmentation, termed JoDiffusion. Firstly, given a standard latent diffusion model, JoDiffusion incorporates an independent annotation variational auto-encoder (VAE) network to map annotation masks into the latent space shared by images. Then, the diffusion model is tailored to capture the joint distribution of each image and its annotation mask conditioned on a text prompt. By doing these, JoDiffusion enables simultaneously generating paired images and semantically consistent annotation masks solely conditioned on text prompts, thereby demonstrating superior scalability. Additionally, a mask optimization strategy is developed to mitigate the annotation noise produced during generation. Experiments on Pascal VOC, COCO, and ADE20K datasets show that the annotated dataset generated by JoDiffusion yields substantial performance improvements in semantic segmentation compared to existing methods.

Pre-training backbone networks on a general annotated dataset (e.g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks. However, those manually collected images often exhibit bias, which is non-transferable across either categories or domains, thus causing the model’s generalization capacity degeneration. To mitigate this problem, we present a low-biased general annotated dataset generation framework (lbGen). Instead of expensive manual collection, we aim at directly generating low-biased images with category annotations. To achieve this goal, we propose to leverage the advantage of a multimodal foundation model (e.g., CLIP), in terms of aligning images in a low-biased semantic space defined by language. Specifically, we develop a bi-level semantic alignment loss, which not only forces all generated images to be consistent with the semantic distribution of all categories belonging to the target dataset in an adversarial learning manner, but also requires each generated image to match the semantic description of its category name. In addition, we further cast an existing image quality scoring model into a quality assurance loss to preserve the quality of the generated image. By leveraging these two loss functions, we can obtain a low-biased image generation model by simply fine-tuning a pre-trained diffusion model using only all category names in the target dataset as input. Experimental results confirm that, compared with the manually labeled dataset or other synthetic datasets, the utilization of our generated low-biased dataset leads to stable generalization capacity enhancement of different backbone networks across various tasks, especially in tasks where the manually labeled samples are scarce. Code is available at: https://github.com/vvvvvjdy/lbGen

Diffusion model has underpinned much recent advances of dataset augmentation in various computer vision tasks. However, when involving generating multi-object images as real scenarios, most existing methods either rely entirely on text condition, resulting in a deviation between the generated objects and the original data, or rely too much on the original images, resulting in a lack of diversity in the generated images, which is of limited help to downstream tasks. To mitigate both problems with one stone, we propose a prompt-free conditional diffusion framework for multi-object image augmentation. Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text, and inject knowledge into the diffusion model through LoRA to alleviate the category deviation between the original model and the target dataset. In addition, we design a reward model based counting loss to assist the traditional reconstruction loss for model training. By constraining the object counts of each category instead of pixel-by-pixel constraints, bridging the quantity deviation between the generated data and the original data while improving the diversity of the generated data. Experimental results demonstrate the superiority of the proposed method over several representative state-of-the-art baselines and showcase strong downstream task gain and out-of-domain generalization capabilities. Code is available at \href{https://github.com/00why00/PFCD}{here}.

We study a novel problem in this paper, that is, if a modern text-to-image diffusion model can tailor any image classifier across domains and categories. Existing domain adaption works exploit both source and target data for domain alignment so as to transfer the knowledge from the labeled source data to the unlabeled target data. However, as the development of text-to-image diffusion models, we wonder if the high-fidelity synthetic data can serve as a surrogate of the source data in real world. In this way, we do not need to collect and annotate the source data for each image classification task in a one-for-one manner. Instead, we utilize only one off-the-shelf text-to-image model to synthesize images with labels derived from text prompts, and then leverage them as a bridge to dig out the knowledge from the task-agnostic text-to-image generator to the task-oriented image classifier via domain adaptation. Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as any unlabeled target data. Extensive experiments validate the feasibility of this idea, which even surprisingly surpasses the state-of-the-art domain adaptation works using the source data collected and annotated in real world.

Few-shot open-set recognition (FSOR) is a challenging task of great practical value. It aims to categorize a sample to one of the predefined, closed-set classes illustrated by few examples while being able to reject the sample from unknown classes. In this work, we approach the FSOR task by proposing a novel energy-based hybrid model. The model is composed of two branches, where a classification branch learns a metric to classify a sample to one of closed-set classes and the energy branch explicitly estimates the open-set probability. To achieve holistic detection of open-set samples, our model leverages both class-wise and pixel-wise features to learn a glocal energy-based score, in which a global energy score is learned using the class-wise features, while a local energy score is learned using the pixel-wise features. The model is enforced to assign large energy scores to samples that are deviated from the few-shot examples in either the class-wise features or the pixel-wise features, and to assign small energy scores otherwise. Experiments on three standard FSOR datasets show the superior performance of our model.11Code is available at https://github.com/00why00/Glocal

Deep neural networks have underpinned much of recent progress in few-shot object detection (FSOD) in remote sensing images. The key lies in accurately inferring the object categories and bounding boxes depending on the feature of each proposal region. However, due to lack of sufficient labeled samples for training model well-fitting, the feature of each proposal fails to be discriminative and informative enough for accurate inference, thus limiting the generalization capacity. To mitigate this problem, we propose a non-local proposal dynamic enhancement learning (NPDEL) methods for FSOD in remote sensing images. In contrast to directly utilizing the proposal features extracted from the backbone, we propose to enhance them before inference using a non-local dynamic enhancement module which first carries out a non-local graph convolution on all proposal features and then dynamically fuses the convolved results with the original features for enhancement. By doing this, the enhanced proposal features can adaptively aggregate the related semantic information from the whole image, thus improving their discriminability as well as the generalization capacity in FSOD. Experiments results on different FSOD tasks demonstrate the efficacy of the proposed method.