CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot abilities for vision-language tasks. In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task. Then we propose a parameter-efficient fine-tuning strategy to boost the few-shot performance on the vqa task. We achieve competitive zero/few-shot results on the visual question answering and visual entailment tasks without introducing any additional pre-training procedure.
Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for natural language understanding (NLU). PERT is an auto-encoding model (like BERT) trained with Permuted Language Model (PerLM). The formulation of the proposed PerLM is straightforward. We permute a proportion of the input text, and the training objective is to predict the position of the original token. Moreover, we also apply whole word masking and N-gram masking to improve the performance of PERT. We carried out extensive experiments on both Chinese and English NLU benchmarks. The experimental results show that PERT can bring improvements over various comparable baselines on some of the tasks, while others are not. These results indicate that developing more diverse pre-training tasks is possible instead of masked language model variants. Several quantitative studies are carried out to better understand PERT, which might help design PLMs in the future. Resources are available: https://github.com/ymcui/PERT
Language-based environment manipulation requires agents to manipulate the environment following natural language instructions, which is challenging due to the huge space of the environments. To address this challenge, various approaches have been proposed in recent work. Although these approaches work well for their intended environments, they are difficult to generalize across environments. In this work, we propose LEMON, a general framework for language-based environment manipulation tasks. Specifically, we first propose a unified approach to deal with various environments using the same generative language model. Then we propose an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre-training corpus. Experimental results on tasks including Alchemy, Scene, Tangrams and ProPara demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on Alchemy, Scene and ProPara, and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.
Deep image steganography is a data hiding technology that conceal data in digital images via deep neural networks. However, existing deep image steganography methods only consider the visual similarity of container images to host images, and neglect the statistical security (stealthiness) of container images. Besides, they usually hides data limited to image type and thus relax the constraint of lossless extraction. In this paper, we address the above issues in a unified manner, and propose deep image steganography that can embed data with arbitrary types into images for secure data hiding and lossless data revealing. First, we formulate the data hiding as an image colorization problem, in which the data is binarized and further mapped into the color information for a gray-scale host image. Second, we design a conditional invertible neural network which uses gray-scale image as prior to guide the color generation and perform data hiding in a secure way. Finally, to achieve lossless data revealing, we present a multi-stage training scheme to manage the data loss due to rounding errors between hiding and revealing processes. Extensive experiments demonstrate that the proposed method can perform secure data hiding by generating realism color images and successfully resisting the detection of steganalysis. Moreover, we can achieve 100% revealing accuracy in different scenarios, indicating the practical utility of our steganography in the real-world.
Semantic Web (SW) technology has been widely applied to many domains such as medicine, health care, finance, geology. At present, researchers mainly rely on their experience and preferences to develop and evaluate the work of SW technology. Although the general architecture (e.g., Tim Berners-Lee's Semantic Web Layer Cake) of SW technology was proposed many years ago and has been well-known, it still lacks a concrete guideline for standardizing the development of SW technology. In this paper, we propose an SW technology index to standardize the development for ensuring that the work of SW technology is designed well and to quantitatively evaluate the quality of the work in SW technology. This index consists of 10 criteria that quantify the quality as a score of 0 ~ 10. We address each criterion in detail for a clear explanation from three aspects: 1) what is the criterion? 2) why do we consider this criterion and 3) how do the current studies meet this criterion? Finally, we present the validation of this index by providing some examples of how to apply the index to the validation cases. We conclude that the index is a useful standard to guide and evaluate the work in SW technology.
3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy. Data collected for other use cases (such as virtual reality, gaming, and animation) may therefore not be usable for AV applications. This necessitates the collection and annotation of a large amount of 3D data for HPE in AV, which is time-consuming and expensive. In this paper, we propose one of the first approaches to alleviate this problem in the AV setting. Specifically, we propose a multi-modal approach which uses 2D labels on RGB images as weak supervision to perform 3D HPE. The proposed multi-modal architecture incorporates LiDAR and camera inputs with an auxiliary segmentation branch. On the Waymo Open Dataset, our approach achieves a 22% relative improvement over camera-only 2D HPE baseline, and 6% improvement over LiDAR-only model. Finally, careful ablation studies and parts based analysis illustrate the advantages of each of our contributions.
Group Activity Recognition (GAR) detects the activity performed by a group of actors in a short video clip. The task requires the compositional understanding of scene entities and relational reasoning between them. We approach GAR by modeling the video as a series of tokens that represent the multi-scale semantic concepts in the video. We propose COMPOSER, a Multiscale Transformer based architecture that performs attention-based reasoning over tokens at each scale and learns group activity compositionally. In addition, we only use the keypoint modality which reduces scene biases and improves the generalization ability of the model. We improve the multi-scale representations in COMPOSER by clustering the intermediate scale representations, while maintaining consistent cluster assignments between scales. Finally, we use techniques such as auxiliary prediction and novel data augmentations (e.g., Actor Dropout) to aid model training. We demonstrate the model's strength and interpretability on the challenging Volleyball dataset. COMPOSER achieves a new state-of-the-art 94.5% accuracy with the keypoint-only modality. COMPOSER outperforms the latest GAR methods that rely on RGB signals, and performs favorably compared against methods that exploit multiple modalities. Our code will be available.
A modern self-supervised learning algorithm typically enforces persistency of the representations of an instance across views. While being very effective on learning holistic image and video representations, such an approach becomes sub-optimal for learning spatio-temporally fine-grained features in videos, where scenes and instances evolve through space and time. In this paper, we present the Contextualized Spatio-Temporal Contrastive Learning (ConST-CL) framework to effectively learn spatio-temporally fine-grained representations using self-supervision. We first design a region-based self-supervised pretext task which requires the model to learn to transform instance representations from one view to another guided by context features. Further, we introduce a simple network design that effectively reconciles the simultaneous learning process of both holistic and local representations. We evaluate our learned representations on a variety of downstream tasks and ConST-CL achieves state-of-the-art results on four datasets. For spatio-temporal action localization, ConST-CL achieves 39.4% mAP with ground-truth boxes and 30.5% mAP with detected boxes on the AVA-Kinetics validation set. For object tracking, ConST-CL achieves 78.1% precision and 55.2% success scores on OTB2015. Furthermore, ConST-CL achieves 94.8% and 71.9% top-1 fine-tuning accuracy on video action recognition datasets, UCF101 and HMDB51 respectively. We plan to release our code and models to the public.
This work presents a self-supervised learning framework named TeG to explore Temporal Granularity in learning video representations. In TeG, we sample a long clip from a video and a short clip that lies inside the long clip. We then extract their dense temporal embeddings. The training objective consists of two parts: a fine-grained temporal learning objective to maximize the similarity between corresponding temporal embeddings in the short clip and the long clip, and a persistent temporal learning objective to pull together global embeddings of the two clips. Our study reveals the impact of temporal granularity with three major findings. 1) Different video tasks may require features of different temporal granularities. 2) Intriguingly, some tasks that are widely considered to require temporal awareness can actually be well addressed by temporally persistent features. 3) The flexibility of TeG gives rise to state-of-the-art results on 8 video benchmarks, outperforming supervised pre-training in most cases.
Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor. The existing methods for SCBSS mainly focus on separating two sources and have weak generalization performance. To address these problems, an algorithm is proposed in this paper to separate multiple sources from a mixture by designing a parallel dual generative adversarial Network (PDualGAN) that can build the relationship between a mixture and the corresponding multiple sources to realize one-to-multiple cross-domain mapping. This algorithm can be applied to any mixed model such as linear instantaneous mixed model and convolutional mixed model. Besides, one-to-multiple datasets are created which including the mixtures and corresponding sources for this study. The experiment was carried out on four different datasets and tested with signals mixed in different proportions. Experimental results show that the proposed algorithm can achieve high performance in peak signal-to-noise ratio (PSNR) and correlation, which outperforms state-of-the-art algorithms.