Search

Additional file 1. Additional figures.

Additional file 1.

Existing neural rendering methods for creating human avatars typically either require dense input signals such as video or multi-view images, or leverage a learned prior from large-scale specific 3D human datasets such that reconstruction can be performed with sparse-view inputs. Most of these methods fail to achieve realistic reconstruction when only a single image is available. To enable the data-efficient creation of realistic animatable 3D humans, we propose ELICIT, a novel method for learning human-specific neural radiance fields from a single image. Inspired by the fact that humans can effortlessly estimate the body geometry and imagine full-body clothing from a single image, we leverage two priors in ELICIT: 3D geometry prior and visual semantic prior. Specifically, ELICIT utilizes the 3D body shape geometry prior from a skinned vertex-based template model (i.e., SMPL) and implements the visual clothing semantic prior with the CLIP-based pre-trained models. Both priors are used to jointly guide the optimization for creating plausible content in the invisible areas. Taking advantage of the CLIP models, ELICIT can use text descriptions to generate text-conditioned unseen regions. In order to further improve visual details, we propose a segmentation-based sampling strategy that locally refines different parts of the avatar. Comprehensive evaluations on multiple popular benchmarks, including ZJU-MoCAP, Human3.6M, and DeepFashion, show that ELICIT has outperformed strong baseline methods of avatar creation when only a single image is available. The code is public for research purposes at https://elicit3d.github.io/, Comment: Project website: https://elicit3d.github.io

Video-text retrieval is a class of cross-modal representation learning problems, where the goal is to select the video which corresponds to the text query between a given text query and a pool of candidate videos. The contrastive paradigm of vision-language pretraining has shown promising success with large-scale datasets and unified transformer architecture, and demonstrated the power of a joint latent space. Despite this, the intrinsic divergence between the visual domain and textual domain is still far from being eliminated, and projecting different modalities into a joint latent space might result in the distorting of the information inside the single modality. To overcome the above issue, we present a novel mechanism for learning the translation relationship from a source modality space $\mathcal{S}$ to a target modality space $\mathcal{T}$ without the need for a joint latent space, which bridges the gap between visual and textual domains. Furthermore, to keep cycle consistency between translations, we adopt a cycle loss involving both forward translations from $\mathcal{S}$ to the predicted target space $\mathcal{T'}$, and backward translations from $\mathcal{T'}$ back to $\mathcal{S}$. Extensive experiments conducted on MSR-VTT, MSVD, and DiDeMo datasets demonstrate the superiority and effectiveness of our LaT approach compared with vanilla state-of-the-art methods.

While large scale pre-training has achieved great achievements in bridging the gap between vision and language, it still faces several challenges. First, the cost for pre-training is expensive. Second, there is no efficient way to handle the data noise which degrades model performance. Third, previous methods only leverage limited image-text paired data, while ignoring richer single-modal data, which may result in poor generalization to single-modal downstream tasks. In this work, we propose an EfficientCLIP method via Ensemble Confident Learning to obtain a less noisy data subset. Extra rich non-paired single-modal text data is used for boosting the generalization of text branch. We achieve the state-of-the-art performance on Chinese cross-modal retrieval tasks with only 1/10 training resources compared to CLIP and WenLan, while showing excellent generalization to single-modal tasks, including text retrieval and text classification.

While contrastive learning greatly advances the representation of sentence embeddings, it is still limited by the size of the existing sentence datasets. In this paper, we present TransAug (Translate as Augmentation), which provide the first exploration of utilizing translated sentence pairs as data augmentation for text, and introduce a two-stage paradigm to advances the state-of-the-art sentence embeddings. Instead of adopting an encoder trained in other languages setting, we first distill a Chinese encoder from a SimCSE encoder (pretrained in English), so that their embeddings are close in semantic space, which can be regraded as implicit data augmentation. Then, we only update the English encoder via cross-lingual contrastive learning and frozen the distilled Chinese encoder. Our approach achieves a new state-of-art on standard semantic textual similarity (STS), outperforming both SimCSE and Sentence-T5, and the best performance in corresponding tracks on transfer tasks evaluated by SentEval., Comment: The result in this paper are obtained under a bug. Because we train our model under an evaluation setting (dropout and batch normalization are 0.), but the dropout in our paper is 0.1. So, there is a big mistake in our paper and is not appropriate to published

Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is especially problematic in high-stakes applications where adversarially-manipulated explanations could impair safety and trustworthiness. Building on a geometric understanding of these attacks presented in recent work, we identify Lipschitz continuity conditions on models' gradient that lead to robust gradient-based attributions, and observe that smoothness may also be related to the ability of an attack to transfer across multiple attribution methods. To mitigate these attacks in practice, we propose an inexpensive regularization method that promotes these conditions in DNNs, as well as a stochastic smoothing technique that does not require re-training. Our experiments on a range of image models demonstrate that both of these mitigations consistently improve attribution robustness, and confirm the role that smooth geometry plays in these attacks on real, large-scale models.

Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments. To explain these black-box architectures there have been many methods applied so the internal decisions can be analyzed and understood. In this paper, built on the top of Score-CAM, we introduce an enhanced visual explanation in terms of visual sharpness called SS-CAM, which produces centralized localization of object features within an image through a smooth operation. We evaluate our method on the ILSVRC 2012 Validation dataset, which outperforms Score-CAM on both faithfulness and localization tasks., Comment: 7 pages, 4 figures and 4 tables

XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers. Overall, XDeep takes a trained deep neural network (DNN) as the input, and generates relevant interpretations as the output with the post-hoc manner. From the functionality perspective, XDeep integrates a wide range of interpretation algorithms from the state-of-the-arts, covering different types of methodologies, and is capable of providing both local explanation and global explanation for DNN when interpreting model behaviours. With the well-documented API designed in XDeep, end-users can easily obtain the interpretations for their deep models at hand with several lines of codes, and compare the results among different algorithms. XDeep is generally compatible with Python 3, and can be installed through Python Package Index (PyPI). The source codes are available at: https://github.com/datamllab/xdeep.

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models for text, tabular and image classification, and the fidelity of it by doing simulated user experiments.

To explore the risk factors, treatment and outcomes of biloma after transcatheter arterial chemoembolization (TACE) for hepatocellular carcinoma (HCC).A total of 481 patients with a diagnosis of HCC underwent TACE at our hospital from January 2011 to December 2013. Biloma was tracked by the follow-ups of computed tomography or magnetic resonance imaging (CT/ MRI) . Retrospective analyses were conducted for their clinical features, treatments and prognosis. The statistically significant factors for univariate analysis were introduced into Logistic regression models for multivariate analysis to obtain the risk factors of biloma post-TACE.There were 43 cases of complicated biloma after TACE. And 38 patients (88.4% ) developed biloma at 0.5-3 months post-TACE while another 5 (9.7%) did so at 3-5 months. The multivariate analysis showed that bile duct dilation, a history of hepatectomy prior to TACE, use of polyvinyl alcohol (PVA) particles and nonsuperselective embolization were the risk factors of biloma formation after TACE. Among 9 symptomatics, there were jaundice (n =2) and fever (n =7). The diameter of bilomas was (8.07 ± 3.53) cm for 9 symptomatics and (2.81 ± 1.26) cm for 35 asymptomatics. And the difference was statistically significant (P0. 01). Nine symptomatic patients underwent percutaneous drainage with tube and biloma diminished (n = 7) and even vanished (n = 2). Only conservative treatment was offered for 35 asymptomatics. During the follow-ups, it showed no change (n = 24) , diminishing (n = 8) and disappearance (n = 2). One case died from a greatly enlarged biloma due to hepatic failure and septic shock via a rupture into abdominal cavity and choleperitonitis.The risk factors of biloma formation after TACE for HCC are bile duct dilation, a history of hepatectomy before TACE, use of PVA particles and nonsuperselective embolization. For symptomatics, drainage must be performed timely and the prognosis is fair. For asymptomatics, regular imaging follow-ups are needed. Drainage must be performed timely when the diameter of biloma increased significantly during the follow-ups.