We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas, where each image is associated with a caption containing a pronoun relationship of subjects and objects in the scene. VisoGender is balanced by gender representation in professional roles, supporting bias evaluation in two ways: i) resolution bias, where we evaluate the difference between pronoun resolution accuracies for image subjects with gender presentations perceived as masculine versus feminine by human annotators and ii) retrieval bias, where we compare ratios of professionals perceived to have masculine and feminine gender presentations retrieved for a gender-neutral search query. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes. While the direction and magnitude of gender bias depends on the task and the model being evaluated, captioning models are generally less biased than Vision-Language Encoders. Dataset and code are available at //github.com/oxai/visogender
相關內容
Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated visual content with the textual concepts described in the prompts. In this paper, we propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff, aimed at improving the alignment between text and images in text-to-image diffusion models. In the coarse semantic re-alignment phase, a novel caption reward, leveraging the BLIP-2 model, is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. Subsequently, the fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view. Experimental results on the MS-COCO benchmark demonstrate that the proposed two-stage coarse-to-fine semantic re-alignment method outperforms other baseline re-alignment techniques by a substantial margin in both visual quality and semantic similarity with the input prompt.
The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N>=3) beyond vision and language. We thus propose LanguageBind, taking the language as the bind across different modalities because the language modality is well-explored and contains rich semantics. Specifically, we freeze the language encoder acquired by VL pretraining, then train encoders for other modalities with contrastive learning. As a result, all modalities are mapped to a shared feature space, implementing multi-modal semantic alignment. While LanguageBind ensures that we can extend VL modalities to N modalities, we also need a high-quality dataset with alignment data pairs centered on language. We thus propose VIDAL-10M with Video, Infrared, Depth, Audio and their corresponding Language, naming as VIDAL-10M. In our VIDAL-10M, all videos are from short video platforms with complete semantics rather than truncated segments from long videos, and all the video, depth, infrared, and audio modalities are aligned to their textual descriptions. After pretraining on VIDAL-10M, we outperform ImageBind by 5.8% R@1 on the MSR-VTT dataset with only 15% of the parameters in the zero-shot video-text retrieval task. Beyond this, our LanguageBind has greatly improved in the zero-shot video, audio, depth, and infrared understanding tasks. For instance, LanguageBind surpassing InterVideo by 1.9% on MSR-VTT, 8.8% on MSVD, 6.3% on DiDeMo, and 4.4% on ActivityNet. On the LLVIP and NYU-D datasets, LanguageBind outperforms ImageBind with 23.8% and 11.1% top-1 accuracy. Code address: //github.com/PKU-YuanGroup/LanguageBind.
We construct an efficient class of increasingly high-order (up to 17th-order) essentially non-oscillatory schemes with multi-resolution (ENO-MR) for solving hyperbolic conservation laws. The candidate stencils for constructing ENO-MR schemes range from first-order one-point stencil increasingly up to the designed very high-order stencil. The proposed ENO-MR schemes adopt a very simple and efficient strategy that only requires the computation of the highest-order derivatives of a part of candidate stencils. Besides simplicity and high efficiency, ENO-MR schemes are completely parameter-free and essentially scale-invariant. Theoretical analysis and numerical computations show that ENO-MR schemes achieve designed high-order convergence in smooth regions which may contain high-order critical points (local extrema) and retain ENO property for strong shocks. In addition, ENO-MR schemes could capture complex flow structures very well.
Full-graph training on graph neural networks (GNN) has emerged as a promising training method for its effectiveness. Full-graph training requires extensive memory and computation resources. To accelerate this training process, researchers have proposed employing multi-GPU processing. However the scalability of existing frameworks is limited as they necessitate maintaining the training data for every layer in GPU memory. To efficiently train on large graphs, we present HongTu, a scalable full-graph GNN training system running on GPU-accelerated platforms. HongTu stores vertex data in CPU memory and offloads training to GPUs. HongTu employs a memory-efficient full-graph training framework that reduces runtime memory consumption by using partition-based training and recomputation-caching-hybrid intermediate data management. To address the issue of increased host-GPU communication caused by duplicated neighbor access among partitions, HongTu employs a deduplicated communication framework that converts the redundant host-GPU communication to efficient inter/intra-GPU data access. Further, HongTu uses a cost model-guided graph reorganization method to minimize communication overhead. Experimental results on a 4XA100 GPU server show that HongTu effectively supports billion-scale full-graph GNN training while reducing host-GPU data communication by 25%-71%. Compared to the full-graph GNN system DistGNN running on 16 CPU nodes, HongTu achieves speedups ranging from 7.8X to 20.2X. For small graphs where the training data fits into the GPUs, HongTu achieves performance comparable to existing GPU-based GNN systems.
Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server. Despite individual studies on how client models are aggregated, and, more recently, on the benefits of ImageNet pre-training, there is a lack of understanding of the effect the architecture chosen for the federation has, and of how the aforementioned elements interconnect. To this end, we conduct the first joint ARchitecture-Initialization-Aggregation study and benchmark ARIAs across a range of medical image classification tasks. We find that, contrary to current practices, ARIA elements have to be chosen together to achieve the best possible performance. Our results also shed light on good choices for each element depending on the task, the effect of normalisation layers, and the utility of SSL pre-training, pointing to potential directions for designing FL-specific architectures and training pipelines.
In this paper, SER_AMPEL, a multi-source dataset for speech emotion recognition (SER) is presented. The peculiarity of the dataset is that it is collected with the aim of providing a reference for speech emotion recognition in case of Italian older adults. The dataset is collected following different protocols, in particular considering acted conversations, extracted from movies and TV series, and recording natural conversations where the emotions are elicited by proper questions. The evidence of the need for such a dataset emerges from the analysis of the state of the art. Preliminary considerations on the critical issues of SER are reported analyzing the classification results on a subset of the proposed dataset.
Adversarial attacks are an important security concern for computer vision (CV), as they enable malicious attackers to reliably manipulate CV models. Existing attacks aim to elicit an output desired by the attacker, but keep the model fully intact on clean data. With CV models becoming increasingly valuable assets in applied practice, a new attack vector is emerging: disrupting the models as a form of economic sabotage. This paper opens up the exploration of damaging adversarial attacks (DAAs) that seek to damage the target model and maximize the total cost incurred by the damage. As a pioneer DAA, this paper proposes Trainwreck, a train-time attack that poisons the training data of image classifiers to degrade their performance. Trainwreck conflates the data of similar classes using stealthy ($\epsilon \leq 8/255$) class-pair universal perturbations computed using a surrogate model. Trainwreck is a black-box, transferable attack: it requires no knowledge of the target model's architecture, and a single poisoned dataset degrades the performance of any model trained on it. The experimental evaluation on CIFAR-10 and CIFAR-100 demonstrates that Trainwreck is indeed an effective attack across various model architectures including EfficientNetV2, ResNeXt-101, and a finetuned ViT-L-16. The strength of the attack can be customized by the poison rate parameter. Finally, data redundancy with file hashing and/or pixel difference are identified as a reliable defense technique against Trainwreck or similar DAAs. The code is available at //github.com/JanZahalka/trainwreck.
Cultural values vary significantly around the world. Despite a large heterogeneity, similarities across national cultures are to be expected. This paper studies cross-country culture heterogeneity via the joint inference of copula graphical models. To this end, a random graph generative model is introduced, with a latent space that embeds cultural relatedness across countries. Taking world-wide country-specific survey data as the primary source of information, the modelling framework allows to integrate external data, both at the level of cultural traits and of their interdependence. In this way, we are able to identify several dimensions of culture.
When modeling scientific and industrial problems, geometries are typically modeled by explicit boundary representations obtained from computer-aided design software. Unfitted (also known as embedded or immersed) finite element methods offer a significant advantage in dealing with complex geometries, eliminating the need for generating unstructured body-fitted meshes. However, current unfitted finite elements on nonlinear geometries are restricted to implicit (possibly high-order) level set geometries. In this work, we introduce a novel automatic computational pipeline to approximate solutions of partial differential equations on domains defined by explicit nonlinear boundary representations. For the geometrical discretization, we propose a novel algorithm to generate quadratures for the bulk and surface integration on nonlinear polytopes required to compute all the terms in unfitted finite element methods. The algorithm relies on a nonlinear triangulation of the boundary, a kd-tree refinement of the surface cells that simplify the nonlinear intersections of surface and background cells to simple cases that are diffeomorphically equivalent to linear intersections, robust polynomial root-finding algorithms and surface parameterization techniques. We prove the correctness of the proposed algorithm. We have successfully applied this algorithm to simulate partial differential equations with unfitted finite elements on nonlinear domains described by computer-aided design models, demonstrating the robustness of the geometric algorithm and showing high-order accuracy of the overall method.
We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. When trained with a modern training strategy using heavy data-augmentation and optionally distillation, it attains surprisingly good accuracy/complexity trade-offs on ImageNet. We will share our code based on the Timm library and pre-trained models.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191