While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies have primarily focused on probing such bias attributes individually while ignoring biases associated with intersections between social attributes. This could be due to the difficulty of collecting an exhaustive set of image-text pairs for various combinations of social attributes. To address this challenge, we employ text-to-image diffusion models to produce counterfactual examples for probing intserctional social biases at scale. Our approach utilizes Stable Diffusion with cross attention control to produce sets of counterfactual image-text pairs that are highly similar in their depiction of a subject (e.g., a given occupation) while differing only in their depiction of intersectional social attributes (e.g., race & gender). Through our over-generate-then-filter methodology, we produce SocialCounterfactuals, a high-quality dataset containing over 171k image-text pairs for probing intersectional biases related to gender, race, and physical characteristics. We conduct extensive experiments to demonstrate the usefulness of our generated dataset for probing and mitigating intersectional social biases in state-of-the-art VLMs.
This paper addresses the challenge of learning a local visual pattern of an object from one image, and generating images depicting objects with that pattern. Learning a localized concept and placing it on an object in a target image is a nontrivial task, as the objects may have different orientations and shapes. Our approach builds upon recent advancements in visual concept learning. It involves acquiring a visual concept (e.g., an ornament) from a source image and subsequently applying it to an object (e.g., a chair) in a target image. Our key idea is to perform in-context concept learning, acquiring the local visual concept within the broader context of the objects they belong to. To localize the concept learning, we employ soft masks that contain both the concept within the mask and the surrounding image area. We demonstrate our approach through object generation within an image, showcasing plausible embedding of in-context learned concepts. We also introduce methods for directing acquired concepts to specific locations within target images, employing cross-attention mechanisms, and establishing correspondences between source and target objects. The effectiveness of our method is demonstrated through quantitative and qualitative experiments, along with comparisons against baseline techniques.
Two difficulties here make low-light image enhancement a challenging task; firstly, it needs to consider not only luminance restoration but also image contrast, image denoising and color distortion issues simultaneously. Second, the effectiveness of existing low-light enhancement methods depends on paired or unpaired training data with poor generalization performance. To solve these difficult problems, we propose in this paper a new learning-based Retinex decomposition of zero-shot low-light enhancement method, called ZERRINNet. To this end, we first designed the N-Net network, together with the noise loss term, to be used for denoising the original low-light image by estimating the noise of the low-light image. Moreover, RI-Net is used to estimate the reflection component and illumination component, and in order to solve the color distortion and contrast, we use the texture loss term and segmented smoothing loss to constrain the reflection component and illumination component. Finally, our method is a zero-reference enhancement method that is not affected by the training data of paired and unpaired datasets, so our generalization performance is greatly improved, and in the paper, we have effectively validated it with a homemade real-life low-light dataset and additionally with advanced vision tasks, such as face detection, target recognition, and instance segmentation. We conducted comparative experiments on a large number of public datasets and the results show that the performance of our method is competitive compared to the current state-of-the-art methods. The code is available at:https://github.com/liwenchao0615/ZERRINNet
Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline.SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios. Project page https://river-zhang.github.io/SIFU-projectpage/ .
Overfitting remains a significant challenge in the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis. Visualizing heatmaps reveals that current MIL methods focus on a subset of predictive instances, hindering effective model generalization. To tackle this, we propose Attention-Challenging MIL (ACMIL), aimed at forcing the attention mechanism to capture more challenging predictive instances. ACMIL incorporates two techniques, Multiple Branch Attention (MBA) to capture richer predictive instances and Stochastic Top-K Instance Masking (STKIM) to suppress simple predictive instances. Evaluation on three WSI datasets outperforms state-of-the-art methods. Additionally, through heatmap visualization, UMAP visualization, and attention value statistics, this paper comprehensively illustrates ACMIL's effectiveness in overcoming the overfitting challenge. The source code is available at \url{https://github.com/dazhangyu123/ACMIL}.
Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation. Therefore, a natural idea is to combine multimodal images for refined and accurate land-cover interpretation. Although many efforts have been attempted to achieve multi-source remote sensing image classification, there are still three issues as follows: 1) indiscriminate feature representation without sufficiently considering modal heterogeneity, 2) abundant features and complex computations associated with modeling long-range dependencies, and 3) overfitting phenomenon caused by sparsely labeled samples. To overcome the above barriers, a transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. Then, a self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling. Finally, a mean forward is put forward in order to avoid overfitting. Based on the above structures, the proposed model is able to break through modal gaps to obtain differentiated graph representation with competitive time cost, even for a small fraction of training samples. Experiments and analyses on three benchmark datasets with various state-of-the-art (SOTA) methods show the performance of the proposed approach.
This paper addresses the problem of super-resolution: constructing a highly resolved (HR) image from a low resolved (LR) one. Recent unsupervised approaches search the latent space of a StyleGAN pre-trained on HR images, for the image that best downscales to the input LR image. However, they tend to produce out-of-domain images and fail to accurately reconstruct HR images that are far from the original domain. Our contribution is twofold. Firstly, we introduce a new regularizer to constrain the search in the latent space, ensuring that the inverted code lies in the original image manifold. Secondly, we further enhanced the reconstruction through expanding the image prior around the optimal latent code. Our results show that the proposed approach recovers realistic high-quality images for large magnification factors. Furthermore, for low magnification factors, it can still reconstruct details that the generator could not have produced otherwise. Altogether, our approach achieves a good trade-off between fidelity and realism for the super-resolution task.
Despite the limited availability and quantum volume of quantum computers, quantum image representation is a widely researched area. Currently developed methods use quantum entanglement to encode information about pixel positions. These methods range from using the angle parameter of the rotation gate (e.g., the Flexible Representation of Quantum Images, FRQI), sequences of qubits (e.g., Novel Enhanced Quantum Representation, NEQR), or the angle parameter of the phase shift gates (e.g., Local Phase Image Quantum Encoding, LPIQE) for storing color information. All these methods are significantly affected by decoherence and other forms of quantum noise, which is an inseparable part of quantum computing in the noisy intermediate-scale quantum era. These phenomena can highly influence the measurements and result in extracted images that are visually dissimilar to the originals. Because this process is at its foundation quantum, the computational reversal of this process is possible. There are many methods for error correction, mitigation, and reduction, but all of them use quantum computer time or additional qubits to achieve the desired result. We report the successful use of a generative adversarial network trained for image-to-image translation, in conjunction with Phase Distortion Unraveling error reduction method, for reducing overall error in images encoded using LPIQE.
Diffusion models have been demonstrated as powerful deep learning tools for image generation in CT reconstruction and restoration. Recently, diffusion posterior sampling, where a score-based diffusion prior is combined with a likelihood model, has been used to produce high quality CT images given low-quality measurements. This technique is attractive since it permits a one-time, unsupervised training of a CT prior; which can then be incorporated with an arbitrary data model. However, current methods only rely on a linear model of x-ray CT physics to reconstruct or restore images. While it is common to linearize the transmission tomography reconstruction problem, this is an approximation to the true and inherently nonlinear forward model. We propose a new method that solves the inverse problem of nonlinear CT image reconstruction via diffusion posterior sampling. We implement a traditional unconditional diffusion model by training a prior score function estimator, and apply Bayes rule to combine this prior with a measurement likelihood score function derived from the nonlinear physical model to arrive at a posterior score function that can be used to sample the reverse-time diffusion process. This plug-and-play method allows incorporation of a diffusion-based prior with generalized nonlinear CT image reconstruction into multiple CT system designs with different forward models, without the need for any additional training. We develop the algorithm that performs this reconstruction, including an ordered-subsets variant for accelerated processing and demonstrate the technique in both fully sampled low dose data and sparse-view geometries using a single unsupervised training of the prior.
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary Pseudo Multi-Modal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Subsequently, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Then PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D Chinese Audio-Visual Facial Animation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. We recommend watching the supplementary video.