This research tackles the problem of generating interaction between two human actors corresponding to textual description. We claim that certain interactions, which we call asymmetric interactions, involve a relationship between an actor and a receiver, whose motions significantly differ depending on the assigned role. However, existing studies of interaction generation attempt to learn the correspondence between a single label and the motions of both actors combined, overlooking differences in individual roles. We consider a novel problem of role-aware interaction generation, where roles can be designated before generation. We translate the text of the asymmetric interactions into active and passive voice to ensure the textual context is consistent with each role. We propose a model that learns to generate motions of the designated role, which together form a mutually consistent interaction. As the model treats individual motions separately, it can be pretrained to derive knowledge from single-person motion data for more accurate interactions. Moreover, we introduce a method inspired by Permutation Invariant Training (PIT) that can automatically learn which of the two actions corresponds to an actor or a receiver without additional annotation. We further present cases where existing evaluation metrics fail to accurately assess the quality of generated interactions, and propose a novel metric, Mutual Consistency, to address such shortcomings. Experimental results demonstrate the efficacy of our method, as well as the necessity of the proposed metric. Our code is available at https://github.com/line/Human-Interaction-Generation.
论文检索
输入标题、作者或关键词，从 2,156 篇学术成果中精准定位
Not all camouflages are equally effective, as even a partially visible contour or a slight color difference can make the animal stand out and break its camouflage. In this paper, we address the question of what makes a camouflage successful, by proposing three scores for automatically assessing its effectiveness. In particular, we show that camouflage can be measured by the similarity between background and foreground features and boundary visibility. We use these camouflage scores to assess and compare all available camouflage datasets. We also incorporate the proposed camouflage score into a generative model as an auxiliary loss and show that effective camouflage images or videos can be synthesised in a scalable manner. The generated synthetic dataset is used to train a transformer-based model for segmenting camouflaged animals in videos. Experimentally, we demonstrate state-of-the-art camouflage breaking performance on the public MoCA-Mask benchmark.
We present a new formulation for structured information extraction (SIE) from visually rich documents. We address the limitations of existing IOB tagging and graph-based formulations, which are either overly reliant on the correct ordering of input text or struggle with decoding a complex graph. Instead, motivated by anchor-based object detectors in computer vision, we represent an entity as an anchor word and a bounding box, and represent entity linking as the association between anchor words. This is more robust to text ordering, and maintains a compact graph for entity linking. The formulation motivates us to introduce 1) a Document Transformer (DocTr) that aims at detecting and associating entity bounding boxes in visually rich documents, and 2) a simple pre-training strategy that helps learn entity detection in the context of language. Evaluations on three SIE benchmarks show the effectiveness of the proposed formulation, and the overall approach outperforms existing solutions.
In this paper we present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step descriptions from a language knowledge base (wikiHow) containing instructional articles for a large variety of procedural tasks. Without any form of manual supervision, our model learns to temporally ground the steps of procedural articles in how-to videos by matching three modalities: frames, narrations, and step descriptions. Specifically, our method aligns steps to video by fusing information from two distinct pathways: i) direct alignment of step descriptions to frames, ii) indirect alignment obtained by composing steps-to-narrations with narrations-to-video correspondences. Notably, our approach performs global temporal grounding of all steps in an article at once by exploiting order information, and is trained with step pseudo-labels which are iteratively refined and aggressively filtered. In order to validate our model we introduce a new benchmark -- HT-Step -- obtained by manually annotating a 124-hour subset of HowTo100M with steps sourced from wikiHow articles. Experiments on this benchmark as well as zero-shot evaluations on CrossTask demonstrate that our multi-modality alignment yields dramatic gains over several baselines and prior works. Finally, we show that our inner module for matching narration-to-video outperforms by a large margin the state of the art on the HTM-Align narration-video alignment benchmark.
Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, analyzing performance around hand-crafted subgroups targeting specific bias dimensions reveals systemic undesirable behaviors. However, this subgroup analysis is frequently stalled by annotation efforts, which require extensive time and resources to collect the necessary data. Prior art attempts to automatically discover subgroups to circumvent these constraints but typically leverages model behavior on existing task-specific annotations and rapidly degrades on more complex inputs beyond "tabular" data, none of which study vision-and-language models. This paper presents VLSlice, an interactive system enabling user-guided discovery of coherent representation-level subgroups with consistent visiolinguistic behavior, denoted as vision-and-language slices, from unlabeled image sets. We show that VLSlice enables users to quickly generate diverse high-coherency slices in a user study (n=22) and release the tool publicly.
Hair editing has made tremendous progress in recent years. Early hair editing methods use well-drawn sketches or masks to specify the editing conditions. Even though they can enable very fine-grained local control, such interaction modes are inefficient for the editing conditions that can be easily specified by language descriptions or reference images. Thanks to the recent breakthrough of cross-modal models (e.g., CLIP), HairCLIP is the first work that enables hair editing based on text descriptions or reference images. However, such text-driven and reference-driven interaction modes make HairCLIP unable to support fine-grained controls specified by sketch or mask. In this paper, we propose HairCLIPv2, aiming to support all the aforementioned interactions with one unified framework. Simultaneously, it improves upon HairCLIP with better irrelevant attributes (e.g., identity, background) preservation and unseen text descriptions support. The key idea is to convert all the hair editing tasks into hair transfer tasks, with editing conditions converted into different proxies accordingly. The editing effects are added upon the input image by blending the corresponding proxy features within the hairstyle or hair color feature spaces. Besides the unprecedented user interaction mode support, quantitative and qualitative experiments demonstrate the superiority of HairCLIPv2 in terms of editing effects, irrelevant attribute preservation and visual naturalness. Our code is available at https://github.com/wty-ustc/HairCLIPv2.
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
PDF ↗In this paper, we investigate the adversarial robustness of vision transformers that are equipped with BERT pretraining (e.g., BEiT, MAE). A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. This observation drives us to rethink the basic differences between these BERT pretraining methods and how these differences affect the robustness against adversarial perturbations. Our empirical analysis reveals that the adversarial robustness of BERT pretraining is highly related to the reconstruction target, i.e., predicting the raw pixels of masked image patches will degrade more adversarial robustness of the model than predicting the semantic context, since it guides the model to concentrate more on medium-/high-frequency components of images. Based on our analysis, we provide a simple yet effective way to boost the adversarial robustness of MAE. The basic idea is using the dataset-extracted domain knowledge to occupy the medium-/high-frequency of images, thus narrowing the optimization space of adversarial perturbations. Specifically, we group the distribution of pretraining data and optimize a set of cluster-specific visual prompts on frequency domain. These prompts are incorporated with input images through prototype-based prompt selection during test period. Extensive evaluation shows that our method clearly boost MAE's adversarial robustness while maintaining its clean performance on ImageNet-1k classification. Our code is available at: https://github.com/shikiw/RobustMAE.
DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings
PDF ↗Many virtual reality applications require massive 3D content, which impels the need for low-cost and efficient modeling tools in terms of quality and quantity. In this paper, we present a Diffusion-augmented Generative model to generate high-fidelity 3D textured meshes that can be directly used in modern graphics engines. Challenges in directly generating textured mesh arise from the instability and texture incompleteness of a hybrid framework which contains conversion between 2D features and 3D space. To alleviate these difficulties, DG3D incorporates a diffusion-based augmentation module into the min-max game between the 3D tetrahedral mesh generator and 2D renderings discriminators, which stabilizes network optimization and prevents mode collapse in vanilla GANs. We also suggest using multi-modal renderings in discrimination to further increase the aesthetics and completeness of generated textures. Extensive experiments on the public benchmark and real scans show that our proposed DG3D outperforms existing state-of-the-art methods by a large margin, i.e., 5% 40% in FID-3D score and 5% 10% in geometry-related metrics. Code is available at https://github.com/seakforzq/DG3D.
We present a Multimodal Backdoor defense technique TIJO (Trigger Inversion using Joint Optimization). Recently Walmer et al. demonstrated successful backdoor attacks on multimodal models for the Visual Question Answering task. Their dual-key backdoor trigger is split across two modalities (image and text), such that the backdoor is activated if and only if the trigger is present in both modalities. We propose TIJO that defends against dual-key attacks through a joint optimization that reverse-engineers the trigger in both the image and text modalities. This joint optimization is challenging in multimodal models due to the disconnected nature of the visual pipeline which consists of an offline feature extractor, whose output is then fused with the text using a fusion module. The key insight enabling the joint optimization in TIJO is that the trigger inversion needs to be carried out in the object detection box feature space as opposed to the pixel space. We demonstrate the effectiveness of our method on the TrojVQA benchmark, where TIJO improves upon the state-of-the-art unimodal methods from an AUC of 0.6 to 0.92 on multimodal dual-key backdoors. Furthermore, our method also improves upon the unimodal baselines on unimodal backdoors. We also present detailed ablation studies as well as qualitative results to provide insights into our algorithm such as the critical importance of overlaying the inverted feature triggers on all visual features during trigger inversion.
SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation
PDF ↗Recently, private inference (PI) has addressed the rising concern over data and model privacy in machine learning inference as a service. However, existing PI frameworks suffer from high computational and communication overheads due to the expensive multi-party computation (MPC) protocols, particularly for large models such as vision transformers (ViT). The majority of this overhead is due to the encrypted softmax operation in each self-attention layer. In this work, we present SAL-ViT with two novel techniques to boost PI efficiency on ViTs. Our first technique is a learnable PI-efficient approximation to softmax, namely, learnable 2Quad (L2Q), that introduces learnable scaling and shifting parameters to the prior 2Quad softmax approximation, enabling improvement in accuracy. Then, given our observation that external attention (EA) presents lower PI latency than widely-adopted self-attention (SA) at the cost of accuracy, we present a selective attention search (SAS) method to integrate the strength of EA and SA. Specifically, for a given lightweight EA ViT, we leverage a constrained optimization procedure to selectively search and replace EA modules with SA alternatives to maximize the accuracy. Our extensive experiments show that our SAL-ViT can averagely achieve 1.28x, 1.28x, 1.14x lower PI latency with 1.79%, 1.41%, and 2.08% higher accuracy compared to the existing alternatives, on CIFAR-10, CIFAR-100, and Tiny-ImageNet, respectively.
Visible-infrared person re-identification (VI-ReID) focuses on matching the pedestrian images of the same identity captured by different modality cameras. The part-based methods achieve great success by extracting fine-grained features from feature maps. But most existing part-based methods employ horizontal division to obtain part features suffering from misalignment caused by irregular pedestrian movements. Moreover, most current methods use Euclidean or cosine distance of the output features to measure the similarity without considering the pedestrian relationships. Misaligned part features and naive inference methods both limit the performance of existing works. We propose a Semantic Alignment and Affinity Inference framework (SAAI), which aims to align latent semantic part features with the learnable prototypes and improve inference with affinity information. Specifically, we first propose semantic-aligned feature learning that employs the similarity between pixel-wise features and learnable prototypes to aggregate the latent semantic part features. Then, we devise an affinity inference module to optimize the inference with pedestrian relationships. Comprehensive experimental results conducted on the SYSU-MM01 and RegDB datasets demonstrate the favorable performance of our SAAI framework. Our code will be released at https://github.com/xiaoye-hhh/SAAI.
Thanks to the excellent global modeling capability of attention mechanisms, the Vision Transformer has achieved better results than ConvNet in many computer tasks. However, in generating hierarchical feature maps, the Transformer still adopts the ConvNet feature aggregation scheme. This leads to the problem that the semantic information of the grid area of image becomes confused after feature aggregation, making it difficult for attention to accurately model global relationships. To address this, we propose the Hierarchy Aware Feature Aggregation framework (HAFA). HAFA enhances the extraction of local features adaptively in shallow layers where semantic information is weak, while is able to aggregate patches with similar semantics in deep layers. The clear semantic information of the aggregated patches, enables the attention mechanism to more accurately model global information at the semantic level. Extensive experiments show that after using the HAFA framework, significant improvements have been achieved relative to the baseline models in image classification, object detection, and semantic segmentation tasks.
Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2x faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap.
Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods. Existing calibration methods such as temperature scaling and mixup work well for networks trained on original large-scale data. However, we find that these methods fail to calibrate networks trained on data distilled from large source datasets. In this paper, we show that distilled data lead to networks that are not calibratable due to (i) a more concentrated distribution of the maximum logits and (ii) the loss of information that is semantically meaningful but unrelated to classification tasks. To address this problem, we propose Masked Temperature Scaling (MTS) and Masked Distillation Training (MDT) which mitigate the limitations of distilled data and achieve better calibration results while maintaining the efficiency of dataset distillation.
DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond
PDF ↗Photometric stereo aims to recover detailed surface shapes from images captured under varying illuminations. However, existing real-world datasets primarily focus on evaluating photometric stereo for general non-Lambertian reflectances and feature bulgy shapes that have a certain height. As shape detail recovery is the key strength of photometric stereo over other 3D reconstruction techniques, and the near-planar surfaces widely exist in cultural relics and manufacturing workpieces, we present a new real-world dataset DiLiGenT-Pi containing 30 near-planar scenes with rich surface details. This dataset enables us to evaluate recent photometric stereo methods specifically for their ability to estimate shape details under diverse materials and to identify open problems such as near-planar surface normal estimation from uncalibrated photometric stereo and surface detail recovery for translucent materials. To inspire future research, this dataset will open soruced at https://photometricstereo.github.io/diligentpi.html.
One-Shot Recognition of Any Material Anywhere Using Contrastive Learning with Physics-Based Rendering
PDF ↗Visual recognition of materials and their states is essential for understanding the world, from determining whether food is cooked, metal is rusted, or a chemical reaction has occurred. However, current image recognition methods are limited to specific classes and properties and can't handle the vast number of material states in the world. To address this, we present MatSim: the first dataset and benchmark for computer vision-based recognition of similarities and transitions between materials and textures, focusing on identifying any material under any conditions using one or a few examples. The dataset contains synthetic and natural images. Synthetic images were rendered using giant collections of textures, objects, and environments generated by computer graphics artists. We use mixtures and gradual transitions between materials to allow the system to learn cases with smooth transitions between states (like gradually cooked food). We also render images with materials inside transparent containers to support beverage and chemistry lab use cases. We use this dataset to train a Siamese net that identifies the same material in different objects, mixtures, and environments. The descriptor generated by this net can be used to identify the states of materials and their subclasses using a single image. We also present the first few-shot material recognition benchmark with natural images from a wide range of fields, including the state of foods and beverages, types of grounds, and many other use cases. We show that a net trained on the MatSim synthetic dataset outperforms state-of-the-art models like Clip on the benchmark and also achieves good results on other unsupervised material classification tasks. Dataset, generation code and trained models have been made available at: https://github.com/ZuseZ4/MatSim-Dataset-Generator-Scripts-And-Neural-net
Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes an Empirical Risk Minimization objective. However, Empirical Risk Minimization is known to suffer from distributional shifts which hurt generalizability to prompts unseen during training. By leveraging the regularization ability of Bayesian methods, we frame prompt learning from the Bayesian perspective and formulate it as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. Our framework is implemented by modeling the input prompt space in a probabilistic manner, as an a priori distribution which makes our proposal compatible with prompt learning approaches that are unconditional or conditional on the image. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space, prevents learning spurious features, and exploits transferable invariant features. This results in better generalization of unseen prompts, even across different datasets and domains. Code available at: https://github.com/saic-fi/Bayesian Prompt-Learning
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video. While camera rotation estimation is a well-studied problem, no previous methods exhibit both high accuracy and acceptable speed in this setting. Because the setting is not addressed well by other datasets, we provide a new dataset and benchmark, with high-accuracy, rigorously verified ground truth, on 17 video sequences. Methods developed for wide baseline stereo (e.g., 5-point methods) perform poorly on monocular video. On the other hand, methods used in autonomous driving (e.g., SLAM) leverage specific sensor setups, specific motion models, or local optimization strategies (lagging batch processing) and do not generalize well to handheld video. Finally, for dynamic scenes, commonly used robustification techniques like RANSAC require large numbers of iterations, and become prohibitively slow. We introduce a novel generalization of the Hough transform on SO(3) to efficiently and robustly find the camera rotation most compatible with optical flow. Among comparably fast methods, ours reduces error by almost 50% over the next best, and is more accurate than any method, irrespective of speed. This represents a strong new performance point for crowded scenes, an important setting for computer vision. The code and the dataset are available at https://fabiendelattre.com/robust-rotation-estimation.
There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representations in light of recent interest in denoising diffusion models. While directly pre-training with diffusion models does not produce strong representations, we condition diffusion models on masked input and formulate diffusion models as masked autoencoders (DiffMAE). Our approach is capable of (i) serving as a strong initialization for downstream recognition tasks, (ii) conducting high-quality image inpainting, and (iii) being effortlessly extended to video where it produces state-of-the-art classification accuracy. We further perform a comprehensive study on the pros and cons of design choices and build connections between diffusion models and masked autoencoders.
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
PDF ↗Weakly-supervised temporal action localization (WTAL) is a practical yet challenging task. Due to large-scale datasets, most existing methods use a network pretrained in other datasets to extract features, which are not suitable enough for WTAL. To address this problem, researchers design several modules for feature enhancement, which improve the performance of the localization module, especially modeling the temporal relationship between snippets. However, all of them omit that ambiguous snippets deliver contradictory information, which would reduce the discriminability of linked snippets. Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission of ambiguous information and enhancing the discriminability of snippet-level representations. Additionally, we propose feature consistency loss to prevent the assimilation of features and drive the graph convolution network to generate more discriminative representations. Extensive experiments on THUMOS14 and ActivityNet1.2 benchmarks demonstrate the effectiveness of DDG-Net, establishing new state-of-the-art results on both datasets. Source code is available at https://github.com/XiaojunTang22/ICCV2023-DDGNet.