Audio-Visual Video Parsing (AVVP) task aims to detect and temporally locate events within audio and visual modalities. Multiple events can overlap in the timeline, making identification challenging. While traditional methods usually focus on improving the early audio-visual encoders to embed more effective features, the decoding phase – crucial for final event classification, often receives less attention. We aim to advance the decoding phase and improve its interpretability. Specifically, we introduce a new decoding paradigm, label semantic-based projection (LEAP), that employs labels texts of event categories, each bearing distinct and explicit semantics, for parsing potentially overlapping events. LEAP works by iteratively projecting encoded latent features of audio/visual segments onto semantically independent label embeddings. This process, enriched by modeling cross-modal (audio/visuallabel) interactions, gradually disentangles event semantics within video segments to refine relevant label embeddings, guaranteeing a more discriminative and interpretable decoding process. To facilitate the LEAP paradigm, we propose a semantic-aware optimization strategy, which includes a novel audio-visual semantic similarity loss function. This function leverages the Intersection over Union of audio and visual events (EIoU) as a novel metric to calibrate audio-visual similarities at the feature level, accommodating the varied event densities across modalities. Extensive experiments demonstrate the superiority of our method, achieving new state-of-the-art performance for AVVP and also enhancing the relevant audio-visual event localization task.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
Quantization is a promising approach to reduce the high computational complexity of image super-resolution (SR) networks. However, low-bit quantization leads to severe accuracy loss in SR networks compared to high-level tasks such as image classification. This is because the feature distributions of the SR networks are significantly divergent for each channel or input image, making it difficult to determine a quantization range. Existing SR quantization works approach this distribution mismatch problem by dynamically adapting quantization ranges to the variant distributions during the test time. However, such a dynamic adaptation incurs additional computational costs that limit the benefits of quantization. Instead, we propose a new quantization-aware training framework that effectively overcomes the distribution mismatch problem in SR networks without the need for dynamic adaptation. Intuitively, the mismatch can be reduced by directly regularizing the distance between the feature to be quantized and the quantization grids during training. However, we observe that mismatch regularization can collide with reconstruction loss during training and adversely affect the SR accuracy. Thus, we avoid the conflict between two losses by regularizing the mismatch only when the gradients of mismatch regularization are cooperative with those of reconstruction loss. Additionally, we introduce a layer-wise weight clipping correcting scheme to find a better quantization range for layer-wise different weights. Experimental results show that our algorithm effectively reduces the distribution mismatch, achieving state-of-the-art performance with minimal computational overhead. Our code will be released.
Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model
PDF ↗In multi-class histopathology nuclei analysis tasks, the lack of training data becomes a main bottleneck for the performance of learning-based methods. To tackle this challenge, previous methods have utilized generative models to increase data by generating synthetic samples. However, existing methods often overlook the importance of considering the context of biological tissues (e.g., shape, spatial layout, and tissue type) in the synthetic data. Moreover, while generative models have shown superior performance in synthesizing realistic histopathology images, none of the existing methods are capable of producing image-label pairs at the same time. In this paper, we introduce a novel framework for co-synthesizing histopathology nuclei images and paired semantic labels using a context-conditioned joint diffusion model. We propose conditioning of a diffusion model using nucleus centroid layouts with structure-related text prompts to incorporate spatial and structural context information into the generation targets. Moreover, we enhance the granularity of our synthesized semantic labels by generating instance-wise nuclei labels using distance maps synthesized concurrently in conjunction with the images and semantic labels. We demonstrate the effectiveness of our framework in generating high-quality samples on multi-institutional, multi-organ, and multi-modality datasets. Our synthetic data consistently outperforms existing augmentation methods in the downstream tasks of nuclei segmentation and classification.
Vision transformers have demonstrated promising results and are core components in many tasks. While existing works have explored diverse interaction or transformation modules to process image tokens, most of them still focus on context feature extraction, supplemented with the spatial information injected through additional positional embedding. However, the local positional information within each image token hinders effective spatial scene modeling, making the learned representation hard to directly adapt to downstream tasks, especially those that require high-resolution fine-tuning or 3D scene understanding. To solve this challenge, we propose SpatialFormer, an efficient vision transformer architecture designed to facilitate adaptive spatial modeling for generalizable image representation learning. Specifically, we accompany the image tokens with a set of adaptive spatial tokens to represent the context and spatial information respectively. Each spatial token is initialized with its positional encoding, augmented with learnable embeddings to introduce essential spatial priors that enhance the context features. We employ a decoder-only architecture to enable efficient interaction between the two types of tokens. Our approach learns transferable image representation with enhanced abilities for scene understanding. Moreover, the generated spatial tokens can serve as enhanced initial queries for task-specific decoders, facilitating adaptations to downstream tasks. Extensive experiments on standard image classification and downstream 2D and 3D perception tasks demonstrate the efficiency and transferability of the proposed SpatialFormer architecture.
Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification
PDF ↗Current multi-instance learning algorithms for pathology image analysis often require a substantial number of Whole Slide Images for effective training but exhibit suboptimal performance in scenarios with limited learning data. In clinical settings, restricted access to pathology slides is inevitable due to patient privacy concerns and the prevalence of rare or emerging diseases. The emergence of the Few-shot Weakly Supervised WSI Classification accommodates the significant challenge of the limited slide data and sparse slide-level labels for diagnosis. Prompt learning based on the pre-trained models (e.g., CLIP) appears to be a promising scheme for this setting; however, current research in this area is limited, and existing algorithms often focus solely on patch-level prompts or confine themselves to language prompts. This paper proposes a multi-instance prompt learning framework enhanced with pathology knowledge, i.e., integrating visual and textual prior knowledge into prompts at both patch and slide levels. The training process employs a combination of static and learnable prompts, effectively guiding the activation of pre-trained models and further facilitating the diagnosis of key pathology patterns. Lightweight Messenger and Summary layers are introduced to model relationships between patches and slides within the same patient data. Additionally, alignment-wise contrastive losses ensure the feature-level alignment between visual and textual learnable prompts for both patches and slides. Our method demonstrates superior performance in three challenging clinical tasks, significantly outperforming comparative few-shot methods.
The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation.Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic preserving loss is proposed to ensure the semantic integrity of the original image content. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of TrojVLM in maintaining original semantic content while triggering specific target text outputs. This study not only uncovers a critical security risk in VLMs and image-to-text generation but also sets a foundation for future research on securing multimodal models against such sophisticated threats.
Pretrained models have become a commodity and offer strong results on a broad range of tasks. As they resort to different learning strategies, they tend to be complementary. In this work, we focus on classification and seek to learn a unique encoder able to take from several of those pretrained models. We aim at even stronger generalization across a variety of classification tasks. We propose to learn such an encoder via multi-teacher distillation. We first thoroughly analyse standard distillation when driven by multiple strong teachers with complementary strengths. Guided by this analysis, we gradually propose improvements to the basic distillation setup. Among those, we enrich the architecture of the encoder with a ladder of expendable projectors, which increases the impact of intermediate features during distillation, and we introduce teacher dropping, a regularization mechanism that better balances the teachers' influence. Our final distillation strategy leads to student models of the same capacity as any of the teachers, while retaining or improving upon the performance of the best teacher for each task.
Scaling up the size of vision models has been the de facto standard to obtain more powerful visual representations. In this work, we discuss the point beyond which larger vision models are not necessary. First, we demonstrate the power of Scaling on Scales (S^2), whereby a pre-trained and frozen smaller vision model (e.g., ViT-B or ViT-L), run over multiple image scales, can outperform larger models (e.g., ViT-H or ViT-G) on classification, segmentation, depth estimation, Multimodal LLM (MLLM) benchmarks, and robotic manipulation. Notably, S^2 achieves state-of-the-art performance in detailed understanding of MLLM on V* benchmark, surpassing models such as GPT-4V. We examine the conditions under which S^2 is a preferred scaling approach compared to scaling on model size. While larger models have the advantage of better generalization on hard examples, we show that features of larger vision models can be well approximated by those of multi-scale smaller models. This suggests most, if not all, of the representations learned by current large pre-trained models can also be obtained from multi-scale smaller models. Our results confirm that a multi-scale smaller model has comparable learning capacity to a larger model, and show that pre-training smaller models with S^2 can match or even exceed the advantage of larger models.
SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments
PDF ↗In this paper, we present SPVLoc, a global indoor localization method that accurately determines the six-dimensional (6D) camera pose of a query image and requires minimal scene-specific prior knowledge and no scene-specific training. Our approach employs a novel matching procedure to localize the perspective camera's viewport, given as an RGB image, within a set of panoramic semantic layout representations of the indoor environment. The panoramas are rendered from an untextured 3D reference model, which only compromises approximate structural information about room shapes, along with door and window annotations. We demonstrate that a straightforward convolutional network structure can successfully achieve image-to-panorama and ultimately image-to-model matching. Through a viewport classification score, we rank reference panoramas and select the best match for the query image. Then, a 6D relative pose is estimated between the chosen panorama and query image. Our experiments demonstrate that this approach not only efficiently bridges the domain gap but also generalizes well to previously unseen scenes that are not part of the training data. Moreover, it achieves superior localization accuracy compared to the state of the art methods and also estimates more degrees of freedom of the camera pose.
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately. We aim to bridge this divide by integrating images and point clouds on a unified transformer model. This approach integrates the modality-specific properties of images and point clouds and achieves fundamental downstream tasks in image and 3D object recognition on a unified transformer model by learning visual-geometric representations. In this work, we introduce Formula-Supervised Visual-Geometric Pre-training (FSVGP), a novel synthetic pre-training method that automatically generates aligned synthetic images and point clouds from mathematical formulas. Through cross-modality supervision, we enable supervised pre-training between visual and geometric modalities. FSVGP also reduces reliance on real data collection, cross-modality alignment, and human annotation. Our experimental results show that FSVGP pre-trains more effectively than VisualAtom and PC-FractalDB across six tasks: image and 3D object classification, detection, and segmentation. These achievements demonstrate FSVGP's superior generalization in image and 3D object recognition and underscore the potential of synthetic pre-training in visual-geometric representation learning.
Spiking Neural Networks (SNNs) offer a biologically inspired approach to computer vision that can lead to more efficient processing of visual data with reduced energy consumption. However, maintaining homeostasis within SNNs is challenging, as it requires continuous adjustment of neural responses to preserve equilibrium and optimal processing efficiency amidst diverse and often unpredictable input signals. In response to these challenges, we propose the Asynchronous Bioplausible Neuron (ABN), a dynamic spike firing mechanism that offers a simple yet potent auto-adjustment to variations in input signals. Its parameters, Membrane Gradient (MG), Threshold Retrospective Gradient (TRG), and Spike Efficiency (SE), make it stand out for its easy implementation, significant effectiveness, and proven reduction in power consumption, a key innovation demonstrated in our experiments. Comprehensive evaluation across various datasets demonstrates ABN's enhanced performance in image classification and segmentation, maintenance of neural equilibrium, and energy efficiency. The code will be publicly available on the GitHub Project Page.
Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopting off-the-shelf models, however, access to their training data is often infeasible or not practical, while most of such models are not originally trained concerning adversarial robustness. In this paper, we develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data. Our intuition is to view recent text-to-image diffusion models as ``adaptable'' denoisers that can be optimized to specify target tasks. Based on this, we propose: (a) to initiate a denoise-and-classify pipeline that offers provable guarantees against adversarial attacks, and (b) to leverage a few synthetic reference images generated from the text-to-image model that enables novel adaptation schemes. Our experiments show that our data-free scheme applied to the pre-trained CLIP could improve the (provable) adversarial robustness of its diverse zero-shot classification derivatives (while maintaining their accuracy), significantly surpassing prior approaches that utilize the full training data. Not only for CLIP, we also demonstrate that our framework is easily applicable for robustifying other visual classifiers efficiently.
This study advances material classification using Spectral Sub-Surface Scattering (S4) measurements. While spectrum and subsurface scattering measurements have, individually, been used extensively in material classification, we argue that the strong spectral dependence of subsurface scattering lends itself to highly discriminative features. However, obtaining S4 measurements requires a time-consuming hyperspectral scan. We avoid this by showing that a carefully chosen 2D projection of the S4 point spread function is sufficient for material estimation; specifically, we show that the parameters defining a physics model for S4 can be estimated from this 2D projection. We also design and implement a novel imaging setup, consisting of a point-array illumination and a spectrally-dispersing camera, to make the 2D projections. Through comprehensive experiments, we demonstrate the superiority of S4 imaging over spectral and sub-surface scattering measurements.
In this paper, we introduce Auto-GAS, the first training-free Generative Architecture Search (GAS) framework enabled by an auto-discovered proxy. Generative models like Generative Adversarial Networks (GANs) are now widely used in many real-time applications. Previous GAS methods use differentiable or evolutionary search to find optimal GAN generators for fast inference and memory efficiency. However, the high computational overhead of these training-based GAS techniques limits their adoption. To improve search efficiency, we explore training-free GAS but find existing zero-cost proxies designed for classification tasks underperform on generation benchmarks. To address this challenge, we develop a custom proxy search framework tailored for GAS tasks to enhance predictive power. Specifically, we construct an information-aware proxy that takes feature statistics as inputs and utilizes advanced transform, encoding, reduction, and augment operations to represent candidate proxies. Then, we employ an evolutionary algorithm to perform crossover and mutation on superior candidates within the population based on correlation evaluation. Finally, we perform generator search without training using the optimized proxy. Thus, Auto-GAS enables automated proxy discovery for GAS while significantly accelerating the search before training stage. Extensive experiments on image generation and image-to-image translation tasks demonstrate that Auto-GAS strikes superior accuracy-speed tradeoffs over state-of-the-art methods. Remarkably, Auto-GAS achieves competitive scores with 110$\times$ faster search than GAN Compression. Codes are available in the Appendix.
Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery
PDF ↗Multimodal image-text contrastive learning has shown that joint representations can be learned across modalities. Here, we show how leveraging multiple views of image data with contrastive learning can improve downstream fine-grained classification performance for species recognition, even when one view is absent. We propose ContRastive Image-remote Sensing Pre-training (CRISP)—a new pre-training task for ground-level and aerial image representation learning of the natural world—and introduce Nature Multi-View (NMV), a dataset of natural world imagery including >3 million ground-level and aerial image pairs for over 6,000 plant taxa across the ecologically diverse state of California. The NMV dataset and accompanying material are available at hf.co/datasets/andyvhuynh/NatureMultiView.
Micro-expressions (MEs) are involuntary and quickly displayed facial expressions that reveal subtle psychological activities. Most previous research typically focused on two separate tasks: micro-expression spotting and recognition. We aim to propose a high-precision "spotting+recognition" method that can spot ME intervals from long videos and recognize their emotional categories. Due to the occurrence sparsity of MEs, there is a significant imbalance between the number of micro-expression intervals and non-micro-expression intervals in long videos. This imbalance makes it challenging for models trained using conventional strategies to distinguish true MEs from noise samples caused by head movements, blinking, and macro-expressions, resulting in a high false-positive-rate and reducing the overall performance. We reduce the number of smooth segments to alter the data distribution within the non-micro-expression (non-ME) category. This adjustment enables the model to focus more on the subtle differences between noise samples and ME samples. To achieve this, we design an ingenious training data preparation strategy: using false positive samples from the initial spotting results as non-ME category samples, and using true positive and false negative samples from the initial spotting as emotion category samples. These are combined as the training data, creating a recognition model capable of both emotion classification and non-ME category determination. Additionally, we propose a three-stage micro-expression analysis method, including ME spotting, ME recognition and non-ME intervals removal module. Our method is validated through five-fold cross-validation experiments on the CAS(ME)² and SAMM Long Video datasets, achieving a overall STRS metric of 0.16, which significantly outperformed baseline methods and demonstrated the effectiveness of our approach.
Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a visual spatial instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to fine-tune a Large Language and Vision Assistant for VSD, which has 13 billion parameters and supports high-resolution images. Finally, a large language model is used to refine the generated sentences, enhancing their diversity and accuracy. LLaVA-VSD demonstrates excellent multimodal conversational capabilities and can follow open-ended instructions to assist with inquiries about object relationships in images.
Visual Spatial Description (VSD) is an emerging image-to-text task which aims at generating descriptions of the spatial relationships between given objects in an image. In this paper, we apply Retrieval-Augmented Generation (RAG) technology in guiding Multimodal Large Language Models (MLLMs) for the task of VSD, complemented by an Adaptive Hallucination Corrector, and further fine-tuning them to bolster semantic understanding and overall model efficacy. We found that our approach demonstrated higher accuracy and fewer hallucination errors in both spatial relationship classification and visual language description tasks within the VSD task, achieving state-of-the-art results.
The Visual Spatial Description Challenge (VSD) is the first competition event focused on visual spatial understanding, organized under the auspices of the ACM Multimedia Conference 2024. The goal of the VSD challenge is to assess the the ability of models and systems to comprehend spatial concepts, relationships and other semantics from a scene presented with visual appearance. The VSD challenge provides two benchmark datasets for three subtasks, i.e., visual spatial relationship classification, single spatial description generation, and open-ended spatial description generation. The challenge details are available on https://lllogen.github.io/vsd-challenge.github.io/.
Recent years have seen a revolution in the creation of synthetic multimedia content. Algorithms with the ability to generate truly convincing images, videos, text and audio capable of fooling any human being. In addition to the possible beneficial uses that this type of technology may have, we must highlight the danger of its misuse for criminal or fraudulent activities. Deepfakes stand out as an example of a potentially dangerous use of these technologies, since they facilitate identity theft and the generation of misinformation. Current solutions are not capable of detecting this type of fake content with sufficient reliability. Therefore, it is crucial to develop new algorithms that solve this problem. This paper presents two methods focusing on the classification and localization of deepfake videos taking into account audio and visual information. These methods were submitted to the ACM 1M Deepfakes Detection Challenge, achieving the highest score in the temporal localization task and a top-five ranking in the classification task.