Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations (UAPs), are much more feasible. Current certified training methods train models robust to single-input perturbations but achieve suboptimal clean and UAP accuracy, thereby limiting their applicability in practical applications. We propose a novel method, CITRUS, for certified training of networks robust against UAP attackers. We show in an extensive evaluation across different datasets, architectures, and perturbation magnitudes that our method outperforms traditional certified training methods on standard accuracy (up to 10.3%) and achieves SOTA performance on the more practical certified UAP accuracy metric.
论文检索
输入标题、作者或关键词，从 2,387 篇学术成果中精准定位
In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training. More specifically, we propose a future prediction network, F-Net, which takes the features of multiple consecutive frames and is trained to predict multi-frame features one time step ahead iteratively. In this way, F-Net learns the underlying motion and correspondence information, and we incorporate its features into the depth decoding process. Additionally, to enrich the learning of multi-frame correspondence cues, we further leverage a reconstruction network, R-Net, which is trained via adaptively masked auto-encoding of multi-frame feature volumes. At inference time, both F-Net and R-Net are used to produce queries to work with the depth decoder, as well as a final refinement network. Through extensive experiments on several benchmarks, i.e., NYUDv2, KITTI, DDAD, and Sintel, which cover indoor, driving, and open-domain scenarios, we show that FutureDepth significantly improves upon baseline models, outperforms existing video depth estimation methods, and sets new state-of-the-art (SOTA) accuracy. Furthermore, FutureDepth is more efficient than existing SOTA video depth estimation models and has similar latencies when comparing to monocular models.
We introduce PartSTAD, a method designed for the task adaptation of 2D-to-3D segmentation lifting. Recent studies have highlighted the advantages of utilizing 2D segmentation models to achieve high-quality 3D segmentation through few-shot adaptation. However, previous approaches have focused on adapting 2D segmentation models for domain shift to rendered images and synthetic text descriptions, rather than optimizing the model specifically for 3D segmentation. Our proposed task adaptation method finetunes a 2D bounding box prediction model with an objective function for 3D segmentation. We introduce weights for 2D bounding boxes for adaptive merging and learn the weights using a small additional neural network. Additionally, we incorporate SAM, a foreground segmentation model on a bounding box, to improve the boundaries of 2D segments and consequently those of 3D segmentation. Our experiments on the PartNet-Mobility dataset show significant improvements with our task adaptation approach, achieving a 7.0%p increase in mIoU and a 5.2%p improvement in mAP@50 for semantic and instance segmentation compared to the SotA few-shot 3D segmentation model. The code will be released publicly later.
UNIKD: UNcertainty-Filtered Incremental Knowledge Distillation for Neural Implicit Representation
PDF ↗Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time training. This is expensive especially for scenarios with large-scale scenes and limited data storage. In view of this, we explore the task of incremental learning for NIRs in this work. We design a student-teacher framework to mitigate the catastrophic forgetting problem. As a result, the student network is able to learn new incoming data while preserving old knowledge simultaneously, aided by a random inquirer and an uncertainty-based filter for effective knowledge merging. Our proposed method is general and thus can be adapted to different implicit representations such as neural radiance field (NeRF) and neural SDF. Extensive experimental results for both 3D reconstruction and novel view synthesis demonstrate the effectiveness of our approach compared to different baselines.
Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong initializations for various tasks, but struggles to capture high-level semantics without further supervised fine-tuning, likely due to the low-level nature of its pixel reconstruction objective. A promising yet unrealized framework is learning representations through masked reconstruction in latent space, combining the locality of MIM with the high-level targets. However, this approach poses significant training challenges as the reconstruction targets are learned in conjunction with the model, potentially leading to trivial or suboptimal solutions. Our study is among the first to thoroughly analyze and address the challenges of such framework, which we refer to as Latent MIM. Through a series of carefully designed experiments and extensive analysis, we identify the source of these challenges, including representation collapsing for joint onlin/target optimization, learning objectives, the high region correlation in latent space and decoding conditioning. By sequentially addressing these issues, we demonstrate that latent MIM can indeed learn high-level representations while retaining the benefits of MIM models.
The important manifestation of robot intelligence is the ability to naturally interact and autonomously make decisions. Traditional approaches to robot control often compartmentalize perception, planning, and decision-making, simplifying system design but limiting the synergy between different information streams. This compartmentalization poses challenges in achieving seamless autonomous reasoning, decision-making, and action execution. To address these limitations, a novel paradigm, named Vision-Language-Action tasks for QUAdruped Robots (QUAR-VLA), has been introduced in this paper. This approach tightly integrates visual information and instructions to generate executable actions, effectively merging perception, planning, and decision-making. The central idea is to elevate the overall intelligence of the robot. Within this framework, a notable challenge lies in aligning fine-grained instructions with visual perception information. This emphasizes the complexity involved in ensuring that the robot accurately interprets and acts upon detailed instructions in harmony with its visual observations. Consequently, we propose QUAdruped Robotic Transformer (QUART), a VLA model to integrate visual information and instructions from diverse modalities as input and generates executable actions for real-world robots and present QUAdruped Robot Dataset (QUARD), a large-scale multi-task dataset including navigation, complex terrain locomotion, and whole-body manipulation tasks for training QUART models. Our extensive evaluation shows that our approach leads to performant robotic policies and enables QUART to obtain a range of generalization capabilities.
Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large training set is not available. However, it often leads to overfitting on the small calibration dataset. Several methods have been proposed to address this issue, yet they still rely on only the calibration set for the quantization and they do not validate the quantized model due to the lack of a validation set. In this work, we propose a novel meta-learning based approach to enhance the performance of post-training quantization. Specifically, to mitigate the overfitting problem, instead of only training the quantized model using the original calibration set without any validation during the learning process as in previous PTQ works, in our approach, we both train and validate the quantized model using two different sets of images. In particular, we propose a meta-learning based approach to jointly optimize a transformation network and a quantized model through bi-level optimization. The transformation network modifies the original calibration data and the modified data will be used as the training set to learn the quantized model with the objective that the quantized model achieves a good performance on the original calibration data. Extensive experiments on the widely used ImageNet dataset with different neural network architectures demonstrate that our approach outperforms the state-of-the-art PTQ methods.
Sign language is one of the most effective communication tools for people with hearing difficulties. Most existing works focus on improving the performance of sign language tasks on RGB videos, which may suffer from degraded recording conditions, such as fast movement of hands with motion blur and textured signer’s appearance. The bio-inspired event camera, which asynchronously captures brightness change with high speed, could naturally perceive dynamic hand movements, providing rich manual clues for sign language tasks. In this work, we aim at exploring the potential of event camera in continuous sign language recognition (CSLR) and sign language translation (SLT). To promote the research, we first collect an event-based benchmark EvSign for those tasks with both gloss and spoken language annotations. EvSign dataset offers a substantial amount of high-quality event streams and an extensive vocabulary of glosses and words, thereby facilitating the development of sign language tasks. In addition, we propose an efficient transformer-based framework for event-based SLR and SLT tasks, which fully leverages the advantages of streaming events. The sparse backbone is employed to extract visual features from sparse events. Then, the temporal coherence is effectively utilized through the proposed local token fusion and gloss-aware temporal aggregation modules. Extensive experimental results are reported on both simulated (PHOENIX14T) and EvSign datasets. Our method performs favorably against existing state-of-the-art approaches with only 0.34% computational cost (0.84G FLOPS per video) and 44.2% network parameters. The project is available at https://zhang-pengyu.github.io/EVSign.
Modality alignment serves as the cornerstone for large multi-modal models (LMMs). However, the impact of different attributes (e.g., data type, quality, and scale) of training data on facilitating effective alignment is still under-explored. In this paper, we delve into the influence of training data on LMMs, uncovering three pivotal findings: 1) Highly detailed captions enable more nuanced vision-language alignment, significantly boosting the performance of LMMs in diverse benchmarks, surpassing outcomes from brief captions or VQA data; 2) Cutting-edge LMMs can be close to the captioning capability of costly human annotators, and open-source LMMs could reach similar quality after lightweight fine-tuning; 3) The performance of LMMs scales with the number of detailed captions, exhibiting remarkable improvements across a range from thousands to millions of captions. Drawing from these findings, we introduce the ShareGPT4V series for advanced modality alignment. It includes ShareGPT4V, consisting of 100K high-quality captions curated from GPT4-Vision; ShareGPT4V-PT, containing 1.2M captions produced by our Share-Captioner that can be close to the captioning capabilities of GPT4-Vision; and ShareGPT4V-7B, a simple yet superior LMM excelling in most multi-modal benchmarks, which realized better alignment based on our large-scale high-quality captions.
Text-to-image generation plays a pivotal role in computer vision and natural language processing by translating textual descriptions into visual representations. However, understanding complex relations in detailed text prompts filled with rich relational content remains a significant challenge. To address this, we introduce a novel task: Logic-Rich Text-to-Image (LRT2I) generation. Unlike conventional image generation tasks that rely on short and structurally simple natural language inputs, our task focuses on intricate text inputs abundant in relational information. To tackle these complexities, we collect the Textual-Visual Logic (TV-Logic) dataset, designed to evaluate the performance of text-to-image generation models across diverse and complex scenarios. Furthermore, we propose a baseline model as a benchmark for this task. Our model comprises three key components: a negative pair discriminator, a relation understanding module, and a multimodality fusion module. These components enhance the model's ability to handle disturbances in informative tokens and prioritize relational elements during image generation.
While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train Neural Radiance Fields (NeRF) with motion-blurred images, commonly encountered in real-world scenarios such as low-light or long-exposure conditions. However, the implicit representation of NeRF struggles to accurately recover intricate details from severely motion-blurred images and cannot achieve real-time rendering. In contrast, recent advancements in 3D Gaussian Splatting achieve high-quality 3D scene reconstruction and real-time rendering by explicitly optimizing point clouds as Gaussian spheres. In this paper, we introduce a novel approach, named BAD-Gaussians (Bundle Adjusted Deblur Gaussian Splatting), which leverages explicit Gaussian representation and handles severe motion-blurred images with inaccurate camera poses to achieve high-quality scene reconstruction. Our method models the physical image formation process of motion-blurred images and jointly learns the parameters of Gaussians while recovering camera motion trajectories during exposure time. In our experiments, we demonstrate that BAD-Gaussians not only achieves superior rendering quality compared to previous state-of-the-art deblur neural rendering methods on both synthetic and real datasets but also enables real-time rendering capabilities.
PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion
PDF ↗Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present PanGu-Draw, a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce Coop-Diffusion, an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model will be released soon on the Ascend platform.
Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of visual cues depends on how often input videos match underlying statistical assumptions. On the other hand, natural language description is an information dense representation of video that implicitly captures saliency without requiring modality-specific assumptions, and has not been explored yet for video MAE. To this end, we introduce a novel text-guided masking strategy (TGM) that masks the video regions with highest correspondence to paired captions. Without leveraging any explicit visual cues for saliency, our text-guided masking is competitive with state-of-the-art masking algorithms such as motion-guided masking. To further benefit from the semantics of natural language for masked reconstruction, we next introduce a unified framework for joint MAE and masked video-text contrastive learning. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE on a variety of video recognition tasks, especially for linear probe. When our TGM is combined within this unified framework, we achieve the best relative performance on five action recognition and one egocentric datasets, highlighting the complementary nature of natural language captions for masked video modeling.
The choice of representation plays a key role in self-driving. Bird’s eye view (BEV) representations have shown remarkable performance in recent years. In this paper, we propose to learn object-centric representations in BEV to distill a complex scene into more actionable information for self-driving. We first learn to place objects into slots with a slot attention model on BEV sequences. Based on these object-centric representations, we then train a transformer to learn to drive as well as reason about the future of other vehicles. We found that object-centric slot representations outperform both scene-level and object-level approaches that use the exact attributes of objects. Slot representations naturally incorporate information about objects from their spatial and temporal context such as position, heading, and speed without explicitly providing it. Our model with slots achieves increased coverage of the provided routes and, consequently, a higher driving score, with a lower variance across multiple runs, affirming slots as a reliable alternative in object-centric approaches. Additionally, we validate our model’s performance as a world model through forecasting experiments, demonstrating its capability to accurately predict future slot representations.
HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance
PDF ↗Text-to-image diffusion models have significantly advanced in conditional image generation. However, these models usually struggle with accurately rendering images featuring humans, resulting in distorted limbs and other anomalies. This issue primarily stems from the insufficient recognition and evaluation of limb qualities in diffusion models. To address this issue, we introduce AbHuman, the first large-scale synthesized human benchmark focusing on anatomical anomalies. This benchmark consists of 56K synthesized human images, each annotated with detailed, bounding-box level labels identifying 147K human anomalies in 18 different categories. Based on this, the recognition of human anomalies can be established, which in turn enhances image generation through traditional techniques such as negative prompting and guidance. To further boost the improvement, we propose HumanRefiner, a novel plug-and-play approach for the coarse-to-fine refinement of human anomalies in text-to-image generation. Specifically, HumanRefiner utilizes a self-diagnostic procedure to detect and correct issues related to both coarse-grained abnormal human poses and fine-grained anomaly levels, facilitating pose-reversible diffusion generation. Experimental results on the AbHuman benchmark demonstrate that HumanRefiner significantly reduces generative discrepancies, achieving a 2.9x improvement in limb quality compared to the state-of-the-art open-source generator SDXL and a 1.4x improvement over DALL-E 3 in human evaluations. The dataset and code will be released.
Existing benchmarks for 3D semantic occupancy prediction in autonomous driving are limited by low resolution (up to [512×512×40] with 0.2m voxel size) and inaccurate annotations, hindering the unification of 3D scene understanding through the occupancy representation. Moreover, previous methods can only generate occupancy predictions at 0.4m resolution or lower, requiring post-upsampling to reach their full resolution (0.2m). The root of these limitations lies in the sparsity, noise, and even errors present in the raw data. In this paper, we overcome these challenges by introducing nuCraft, a high-resolution and accurate semantic occupancy dataset derived from nuScenes. nuCraft offers an 8× increase in resolution ([1024 × 1024 × 80] with voxel size of 0.1m) and more precise semantic annotations compared to previous benchmarks. To address the high memory cost of high-resolution occupancy prediction, we propose VQ-Occ, a novel method that encodes occupancy data into a compact latent feature space using a VQ-VAE. This approach simplifies semantic occupancy prediction into feature simulation in the VQ latent space, making it easier and more memory-efficient. Our method enables direct generation of semantic occupancy fields at high resolution without post-upsampling, facilitating a more unified approach to 3D scene understanding. We validate the superior quality of nuCraft and the effectiveness of VQ-Occ through extensive experiments, demonstrating significant advancements over existing benchmarks and methods.
Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed due to the introduction of image features. To construct safe MLLMs, we propose ECSO (Eyes Closed, Safety On), a novel training-free protecting approach that exploits the inherent safety awareness of MLLMs, and generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of the pre-aligned LLMs in MLLMs. Experiments with five state-of-the-art (SOTA) MLLMs demonstrate that ECSO significantly enhances model safety (e.g., a 37.6% improvement on MM-SafetyBench (SD+OCR), and 71.3% on VLSafe for LLaVA-1.5-7B), while consistently maintaining utility results on common MLLM benchmarks. Furthermore, we demonstrate that ECSO can be used as a data engine to generate supervised-finetuning (SFT) data for the alignment of MLLMs without extra human intervention.
3D head animation has seen major quality and runtime improvements over the last few years, particularly empowered by the advances in differentiable rendering and neural radiance fields. Real-time rendering is a highly desirable goal for real-world applications. We propose HeadGaS, a model that uses 3D Gaussian Splats (3DGS) for 3D head reconstruction and animation. In this paper we introduce a hybrid model that extends the explicit 3DGS representation with a base of learnable latent features, which can be linearly blended with low-dimensional parameters from parametric head models to obtain expression-dependent color and opacity values. We demonstrate that HeadGaS delivers state-of-the-art results in real-time inference frame rates, surpassing baselines by up to 2 dB, while accelerating rendering speed by over x10.
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.
Distillation-aware Architecture Search (DAS) seeks to discover the ideal student architecture that delivers superior performance by distilling knowledge from a given teacher model. Previous DAS methods involve time-consuming training-based search processes. Recently, the training-free DAS method (\ie, DisWOT) proposes KD-based proxies and achieves significant search acceleration. However, we observe that DisWOT suffers from limitations such as the need for manual design and poor generalization to diverse architectures, such as the Vision Transformer (ViT). To address these issues, we present Auto-DAS, an automatic proxy discovery framework using an Evolutionary Algorithm (EA) for training-free DAS. Specifically, we empirically find that proxies conditioned on student instinct statistics and teacher-student interaction statistics can effectively predict distillation accuracy. Then, we represent the proxy with computation graphs and construct the proxy search space using instinct and interaction statistics as inputs. To identify promising proxies, our search space incorporates various types of basic transformations and network distance operators inspired by previous proxy and KD-loss designs. Next, our EA initializes populations, evaluates, performs crossover and mutation operations, and selects the best correlation candidate with distillation accuracy. We introduce an adaptive-elite selection strategy to enhance search efficiency and strive for a balance between exploitation and exploration. Finally, we conduct training-free DAS with discovered proxy before the optimal student distillation phase. In this way, our auto-discovery framework eliminates the need for manual design and tuning, while also adapting to different search spaces through direct correlation optimization. Extensive experiments demonstrate that Auto-DAS generalizes well to various architectures and search spaces (\eg, ResNet, ViT, NAS-Bench-101, and NAS-Bench-201), achieving state-of-the-art results in both ranking correlation and final searched accuracy. Code is included in the supplementary materials.