论文检索

Zhengming Zhou, Qiulei Dong

Monocular and binocular self-supervised depth estimations are two important and related tasks in computer vision, which aim to predict scene depths from single images and stereo image pairs respectively. In literature, the two tasks are usually tackled separately by two different kinds of models, and binocular models generally fail to predict depth from single images, while the prediction accuracy of monocular models is generally inferior to binocular models. In this paper, we propose a Two-in-One self-supervised depth estimation network, called TiO-Depth, which could not only compatibly handle the two tasks, but also improve the prediction accuracy. TiO-Depth employs a Siamese architecture and each sub-network of it could be used as a monocular depth estimation model. For binocular depth estimation, a Monocular Feature Matching module is proposed for incorporating the stereo knowledge between the two images, and the full TiO-Depth is used to predict depths. We also design a multi-stage joint-training strategy for improving the performances of TiO-Depth in both two tasks by combining the relative advantages of them. Experimental results on the KITTI, Cityscapes, and DDAD datasets demonstrate that TiO-Depth outperforms both the monocular and binocular state-of-the-art methods in most cases, and further verify the feasibility of a two-in-one network for monocular and binocular depth estimation. The code is available at https://github.com/ZM-Zhou/TiO-Depth_pytorch.

Dongwon Kim, Namyup Kim, Cuiling Lan, Suha Kwak

Referring image segmentation, the task of segmenting any arbitrary entities described in free-form texts, opens up a variety of vision applications. However, manual labeling of training data for this task is prohibitively costly, leading to lack of labeled data for training. We address this issue by a weakly supervised learning approach using text descriptions of training images as the only source of supervision. To this end, we first present a new model that discovers semantic entities in input image and then combines such entities relevant to text query to predict the mask of the referent. We also present a new loss function that allows the model to be trained without any further supervision. Our method was evaluated on four public benchmarks for referring image segmentation, where it clearly outperformed the existing method for the same task and recent open-vocabulary segmentation models on all the benchmarks.

Borui Jiang, Yang Jin, Zhentao Tan, Yadong Mu

Video action segmentation refers to the task of densely casting each video frame or short segment in an untrimmed video into some pre-specified action categories. Although recent years have witnessed a great promise in the development of action segmentation techniques.A large body of existing methods still rely on frame-wise segmentation, which tends to render fragmentary results (i.e., over-segmentation).To effectively address above issues, we here propose a video action segmentation model that implements the novel idea of Refined Temporal Keypoints (RTK) for overcoming caveats of existing methods.To act effectively, the proposed model initially seeks for high-quality, sparse temporal keypoints by extracting non-local cues from the video, rather than conducting frame-wise classification as in many competing methods.Afterwards, large improvements over the inital temporal keypoints are pin-pointed as contributions by further refining and re-assembling operations. In specific, we develop a graph matching module that aggregates structural information between different temporal keypoints by learning the corresponding relationship of the temporal source graphs and the annotated target graphs. The initial temporal keypoints are refined by the encoded structural information reusing the graph matching module.A few set of prior rules are harnessed for post-processing and re-assembling all temporal keypoints.The remaining temporal keypoiting going through all refinement are used to generate the final action segmentation results.We perform experiments on three popular datasets: 50salads, GTEA and Breakfast, and our methods significantly outperforms the current methods, particularly achieves the state-of-the-art F1@50 scores of 83.4%, 79.5%, and 60.5% on three datasets, respectively.

Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette

Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some uncommon conditions. In this paper, we propose the task of 'Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i.e., a prompt. First, we leverage a pretrained contrastive vision-language model (CLIP) to optimize affine transformations of source features, steering them towards the target text embedding while preserving their content and semantics. To achieve this, we propose Prompt-driven Instance Normalization (PIN). Second, we show that these prompt-driven augmentations can be used to perform zero-shot domain adaptation for semantic segmentation. Experiments demonstrate that our method significantly outperforms CLIP-based style transfer baselines on several datasets for the downstream task at hand, even surpassing one-shot unsupervised domain adaptation. A similar boost is observed on object detection and image classification. The code is available at https://github.com/astra-vision/PODA .

William Thong, Przemyslaw Joniak, Alice Xiang

This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. Subsequently, fairness researchers and practitioners have adopted the Fitzpatick skin type classification as a common measure to assess skin color bias in computer vision systems. While effective, the Fitzpatick scale only focuses on the skin tone ranging from light to dark. Towards a more comprehensive measure of skin color, we introduce the hue angle ranging from red to yellow. When applied to images, the hue dimension reveals additional biases related to skin color in both computer vision datasets and models. We then recommend multidimensional skin color scales, relying on both skin tone and hue, for fairness assessments.

Konstantin Pakulev, Alexander Vakhitov, Gonzalo Ferrer

Learning a feature point detector presents a challenge both due to the ambiguity of the definition of a keypoint and, correspondingly, the need for specially prepared ground truth labels for such points. In our work, we address both of these issues by utilizing a combination of a hand-crafted Shi-Tomasi detector, a specially designed metric that assesses the quality of keypoints, the stability score (SS), and a neural network. We build on the principled and localized keypoints provided by the Shi-Tomasi detector and learn the neural network to select good feature points via the stability score. The neural network incorporates the knowledge from the training targets in the form of the neural stability score (NeSS). Therefore, our method is named NeSS-ST since it combines the Shi-Tomasi detector and the properties of the neural stability score. It only requires sets of images for training without dataset pre-labeling or the need for reconstructed correspondence labels. We evaluate NeSS-ST on HPatches, ScanNet, MegaDepth and IMC-PT demonstrating state-of-the-art performance and good generalization on downstream tasks. The project repository is available at: https://github.com/KonstantinPakulev/NeSS-ST.

Patrick Esser, Johnathan Chiu, Parmida Atighehchian, Jonathan Granskog, Anastasis Germanidis

Text-guided generative diffusion models unlock powerful image creation and editing tools. Recent approaches that edit the content of footage while retaining structure require expensive re-training for every input or rely on error-prone propagation of image edits across frames. In this work, we present a structure and content-guided video diffusion model that edits videos based on descriptions of the desired output. Conflicts between user-provided content edits and structure representations occur due to insufficient disentanglement between the two aspects. As a solution, we show that training on monocular depth estimates with varying levels of detail provides control over structure and content fidelity. A novel guidance method, enabled by joint video and image training, exposes explicit control over temporal consistency. Our experiments demonstrate a wide variety of successes; fine-grained control over output characteristics, customization based on a few reference images, and a strong user preference towards results by our model.

Shengjiang Quan, Masahiro Hirano, Yuji Yamakawa

This work investigates the functionality of Semantic information in Contrastive Learning (SemCL). An advanced pretext task is designed: a contrast is performed between each object and its environment, taken from a scene. This allows the SemCL pretrained model to extract objects from their environment in an image, significantly improving the spatial understanding of the pretrained models. Downstream tasks of semantic/instance segmentation, object detection and depth estimation are implemented on PASCAl VOC, Cityscapes, COCO, KITTI, etc. SemCL pretrained models substantially outperform ImageNet pretrained counterparts and are competitive with well-known works on downstream tasks. The results suggest that a dedicated pretext task leveraging semantic information can be powerful in benchmarks related to spatial understanding. The code is available at https://github.com/sjiang95/semcl.

Hong Li, Xingyu Li, Pengbo Hu, Yinuo Lei, Chunxiao Li, Yi Zhou

While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-optimal performance of the jointly trained model to the modality competition phenomenon. Existing works attempt to improve the jointly trained model by modulating the training process. Despite their effectiveness, those methods can only apply to late fusion models. More importantly, the mechanism of the modality competition remains unexplored. In this paper, we first propose an adaptive gradient modulation method that can boost the performance of multi-modal models with various fusion strategies. Extensive experiments show that our method surpasses all existing modulation methods. Furthermore, to have a quantitative understanding of the modality competition and the mechanism behind the effectiveness of our modulation method, we introduce a novel metric to measure the competition strength. This metric is built on the mono-modal concept, a function that is designed to represent the competition-less state of a modality. Through systematic investigation, our results confirm the intuition that the modulation encourages the model to rely on the more informative modality. In addition, we find that the jointly trained model typically has a preferred modality on which the competition is weaker than other modalities. However, this preferred modality need not dominate others. Our code will be available at https://github.com/lihong2303/AGM_ICCV2023.

Jiawei Liu, Changkun Ye, Shan Wang, Ruikai Cui, Jing Zhang, Kaihao Zhang, Nick Barnes

For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary classification models are prone to being over-confident. To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image. ASLP employs our proposed Self-Calibrating Binary Cross Entropy (SC-BCE) loss, which unifies label perturbation processes including stochastic approaches (like DisturbLabel), and label smoothing, to correct calibration while maintaining classification rates. ASLP follows Maximum Entropy Inference of classic statistical mechanics to maximise prediction entropy with respect to missing information. It performs this while: (1) preserving classification accuracy on known data as a conservative solution, or (2) specifically improves model calibration degree by minimising the gap between the prediction accuracy and expected confidence of target training label. Extensive results demonstrate that ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data.

Changsong Wen, Xin Zhang, Xingxu Yao, Jufeng Yang

Label distribution learning (LDL) is a recent hot topic, in which ambiguity is modeled via description degrees of the labels. However, in common LDL tasks, e.g., age estimation, labels are in an intrinsic order. The conventional LDL paradigm adopts a per-label manner for optimization, neglecting the internal sequential patterns of labels. Therefore, we propose a new paradigm, termed ordinal label distribution learning (OLDL). We model the sequential patterns of labels from aspects of spatial, semantic, and temporal order relationships. The spatial order depicts the relative position between arbitrary labels. We build cross-label transformation between distributions, which is determined by the spatial margin in labels. Labels naturally yield different semantics, so the semantic order is represented by constructing semantic correlations between arbitrary labels. The temporal order describes that the presence of labels is determined by their order, i.e. five after four. The value of a particular label contains information about previous labels, and we adopt cumulative distribution to construct this relationship. Based on these characteristics of ordinal labels, we propose the learning objectives and evaluation metrics for OLDL, namely CAD, QFD, and CJS. Comprehensive experiments conducted on four tasks demonstrate the superiority of OLDL against other existing LDL methods in both traditional and newly proposed metrics. Our project page can be found at https://downdric23.github.io/.

Qingyang Wang, Mike A. Powell, Ali Geisa, Eric Bridgeford, Carey E. Priebe, Joshua T. Vogelstein

Why do brains have inhibitory connections? Why do deep networks have negative weights? We propose an answer from the perspective of representation capacity. We believe representing functions is the primary role of both (i) the brain in natural intelligence, and (ii) deep networks in artificial intelligence. Our answer to why there are inhibitory/negative weights is: to learn more functions. We prove that, in the absence of negative weights, neural networks with non-decreasing activation functions are not universal approximators. While this may be an intuitive result to some, to the best of our knowledge, there is no formal theory, in either machine learning or neuroscience, that demonstrates why negative weights are crucial in the context of representation capacity. Further, we provide insights on the geometric properties of the representation space that non-negative deep networks cannot represent. We expect these insights will yield a deeper understanding of more sophisticated inductive priors imposed on the distribution of weights that lead to more efficient biological and machine learning.

Xuanhua He, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, Man Zhou

Pan-sharpening, a panchromatic image guided low-spatial-resolution multi-spectral super-resolution task, aims to reconstruct the missing high-frequency information of high-resolution multi-spectral counterpart. Although the inborn connection with frequency domain, existing pan-sharpening research has almost investigated the potential solution upon frequency domain, thus limiting the model performance improvement. To this end, we first revisit the degradation process of pan-sharpening in Fourier space, and then devise a Pyramid Dual Domain Injection Pan-sharpening Network upon the above observation by fully exploring and exploiting the distinguished information in both the spatial and frequency domains. Specifically, the proposed network is organized with multi-scale U-shape manner and composed by two core parts: a spatial guidance pyramid sub-network for fusing local spatial information and a frequency guidance pyramid sub-network for fusing global frequency domain information, thus encouraging dual-domain complementary learning. In this way, the model can capture multi-scale dual-domain information to enable generating high-quality pan-sharpening results. Quantitative and qualitative experiments over multiple datasets demonstrate that our method performs the best against other state-of-the-art ones and comprises a strong generalization ability for real-world scenes.

Yanzhao Zheng, Yunzhou Shi, Yuhao Cui, Zhongzhou Zhao, Zhiling Luo, Wei Zhou

Generating life-like whole-body human grasping has garnered significant attention in the field of computer graphics. Existing works have demonstrated the effectiveness of keyframe-guided motion generation framework, witch focus on modeling the grasping motions of humans in temporal sequence when the target objects are placed in front of them. However, the generated grasping poses of the human body in the key-frames are limited, failing to capture the full range of grasping poses that humans are capable of. To address this issue, we propose a novel framework called COOP (DeCOupling and COupling of Whole-Body GrasPing Pose Generation) to synthesize life-like whole-body poses that cover the widest range of human grasping capabilities. In this framework, we first decouple the whole-body pose into body pose and hand pose and model them separately, which allows us to pre-train the body model with out-of-domain data easily. Then, we couple these two generated body parts through a unified optimization algorithm. Furthermore, we design a simple evaluation method to evaluate the generalization ability of models in generating grasping poses for objects placed at different positions. The experimental results demonstrate the efficacy and superiority of our method. And COOP holds great potential as a plug-and-play component for other domains in whole-body pose generation. Our models and code are available at https://github.com/zhengyanzhao1997/COOP.

Ding Ma, Xiangqian Wu

The main challenge of Tracking by Natural Language Specification (TNL) is to predict the movement of the target object by giving two heterogeneous information, e.g., one is the static description of the main characteristics of a video contained in the textual query, i.e., long-term context; the other one is an image patch containing the object and its surroundings cropped from the current frame, i.e., the search area. Currently, most methods still struggle with the rationality of using those two information and simply fusing the two. However, the linguistic information contained in the textual query and the visual representation stored in the search area may sometimes be inconsistent, in which case the direct fusion of the two may lead to conflicts. To address this problem, we propose DecoupleTNL, introducing a video clip containing short-term context information into the framework of TNL and exploring a proper way to reduce the impact when visual representation is inconsistent with linguistic information. Concretely, we design two jointly optimized tasks, i.e., short-term context-matching and long-term context-perceiving. The context-matching task aims to gather the dynamic short-term context information in a period, while the context-perceiving task tends to extract the static long-term context information. After that, we design a long short-term modulation module to integrate both context information for accurate tracking. Extensive experiments have been conducted on three tracking benchmark datasets to demonstrate the superiority of DecoupleTNL

Bo Dai, Linge Wang, Baoxiong Jia, Zeyu Zhang, Song-Chun Zhu, Chi Zhang, Yixin Zhu

Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy. Nonetheless, replicating this level of intuitive physics in artificial intelligence (AI) remains a formidable challenge. This study introduces X-VoE, a comprehensive benchmark dataset, to assess AI agents' grasp of intuitive physics. Built on the developmental psychology-rooted Violation of Expectation (VoE) paradigm, X-VoE establishes a higher bar for the explanatory capacities of intuitive physics models. Each VoE scenario within X-VoE encompasses three distinct settings, probing models' comprehension of events and their underlying explanations. Beyond model evaluation, we present an explanation-based learning system that captures physics dynamics and infers occluded object states solely from visual sequences, without explicit occlusion labels. Experimental outcomes highlight our model's alignment with human commonsense when tested against X-VoE. A remarkable feature is our model's ability to visually expound VoE events by reconstructing concealed scenes. Concluding, we discuss the findings' implications and outline future research directions. Through X-VoE, we catalyze the advancement of AI endowed with human-like intuitive physics capabilities.

Zhengzhong Tu, Peyman Milanfar, Hossein Talebi

Image resizing operation is a fundamental preprocessing module in modern computer vision. Throughout the deep learning revolution, researchers have overlooked the potential of alternative resizing methods beyond the commonly used resizers that are readily available, such as nearest-neighbors, bilinear, and bicubic. The key question of our interest is whether the front-end resizer affects the performance of deep vision models? In this paper, we present an extremely lightweight multilayer Laplacian resizer with only a handful of trainable parameters, dubbed MULLER resizer. MULLER has a bandpass nature in that it learns to boost details in certain frequency subbands that benefit the downstream recognition models. We show that MULLER can be easily plugged into various training pipelines, and it effectively boosts the performance of the underlying vision task with little to no extra cost. Specifically, we select a state-of-the-art vision Transformer, MaxViT, as the baseline, and show that, if trained with MULLER, MaxViT gains up to 0.6% top-1 accuracy, and meanwhile enjoys 36% inference cost saving to achieve similar top-1 accuracy on ImageNet-1k, as compared to the standard training scheme. Notably, MULLER's performance also scales with model size and training data size such as ImageNet-21k and JFT, and it is widely applicable to multiple vision tasks, including image classification, object detection and segmentation, as well as image quality assessment. The code is available at https://github.com/google-research/google-research/tree/master/muller.

Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Stefano Soatto

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary. In contrast, we seek to approximate representations from an encoder as combinations of a smaller set of vectors in the embedding space. These vectors can be seen as "ideal words" for generating concepts directly within embedding space of the model. We first present a framework for understanding compositional structures from a geometric perspective. We then explain what these compositional structures entail probabilistically in the case of VLM embeddings, providing intuitions for why they arise in practice. Finally, we empirically explore these structures in CLIP's embeddings and we evaluate their usefulness for solving different vision-language tasks such as classification, debiasing, and retrieval. Our results show that simple linear algebraic operations on embedding vectors can be used as compositional and interpretable methods for regulating the behavior of VLMs.

Quewei Li, Feichao Li, Jie Guo, Yanwen Guo

We propose UHDNeRF, a new framework for novel view synthesis on the challenging ultra-high-resolution (e.g., 4K) real-world scenes. Previous NeRF methods are not specifically designed for rendering on extremely high resolutions, leading to burry results with notable detail-losing problems even though trained on 4K images. This is mainly due to the mismatch between the high-resolution inputs and the low-dimensional volumetric representation. To address this issue, we introduce an adaptive implicit-explicit scene representation with which an explicit sparse point cloud is used to boost the performance of an implicit volume on modeling subtle details. Specifically, we reconstruct the complex real-world scene with a frequency separation strategy that the implicit volume learns to represent the low-frequency properties of the whole scene, and the sparse point cloud is used for reproducing high-frequency details. To better explore the information embedded in the point cloud, we extract a global structure feature and a local point-wise feature from the point cloud for each sample located in the high-frequency regions. Furthermore, a patch-based sampling strategy is introduced to reduce the computational cost. The high-fidelity rendering results demonstrate the superiority of our method for retaining high-frequency details at 4K ultra-high-resolution scenarios against state-of-the-art NeRF-based solutions.

Xiuzhe Wu, Pengfei Hu, Yang Wu, Xiaoyang Lyu, Yan-Pei Cao, Ying Shan, Wenming Yang, Zhongqian Sun, Xiaojuan Qi

Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and appearances on limited facial areas (e.g., lip area) are mainly driven by the input speech. Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training. We thus propose a decomposition-synthesis-composition framework named Speech to Lip (Speech2Lip) that disentangles speech-sensitive and speech-insensitive motion/appearance to facilitate effective learning from limited training data, resulting in the generation of natural-looking videos. First, given a fixed head pose (i.e., canonical space), we present a speech-driven implicit model for lip image generation which concentrates on learning speech-sensitive motion and appearance. Next, to model the major speech-insensitive motion (i.e., head movement), we introduce a geometry-aware mutual explicit mapping (GAMEM) module that establishes geometric mappings between different head poses. This allows us to paste generated lip images at the canonical space onto head images with arbitrary poses and synthesize talking videos with natural head movements. In addition, a Blend-Net and a contrastive sync loss are introduced to enhance the overall synthesis performance. Quantitative and qualitative results on three benchmarks demonstrate that our model can be trained by a video of just a few minutes in length and achieve state-of-the-art performance in both visual quality and speech-visual synchronization. Code: https://github.com/CVMI-Lab/Speech2Lip.