Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

Large-scale datasets play a vital role in computer vision. Existing datasets are either collected according to heuristic label systems or annotated blindly without differentiation to samples, making them inefficient and unscalable. How to systematically collect, annotate and build a mega-scale dataset remains an open question. In this work, we advocate building a high-quality vision dataset actively and continually on a comprehensive label system. Specifically, we contribute Bamboo Dataset, a mega-scale and information-dense dataset for both classification and detection. Bamboo aims to populate the comprehensive categories with 69M image classification annotations and 170,586 object bounding box annotations. Compared to ImageNet22K and Objects365, models pre-trained on Bamboo achieve superior performance among various downstream tasks (6.2% gains on classification and 2.1% gains on detection). In addition, we provide valuable observations regarding large-scale pre-training from over 1,000 experiments. Due to its scalable nature on both label system and annotation pipeline, Bamboo will continue to grow and benefit from the collective efforts of the community, which we hope would pave the way for more general vision models.

Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is because researchers do not choose consistent training recipes and even use different data, hampering the fair comparison between different methods. In this work, we propose CLIP-benchmark, a first attempt to evaluate, analyze, and benchmark CLIP and its variants. We conduct a comprehensive analysis of three key factors: data, supervision, and model architecture. We find considerable intuitive or counter-intuitive insights: (1). Data quality has a significant impact on performance. (2). Certain supervision has different effects for Convolutional Networks (ConvNets) and Vision Transformers (ViT). Applying more proper supervision can effectively improve the performance of CLIP. (3). Curtailing the text encoder reduces the training cost but not much affect the final performance. Moreover, we further combine DeCLIP with FILIP, bringing us the strongest variant DeFILIP. The CLIP-benchmark would be released at: https://github.com/Sense-GVT/DeCLIP for future CLIP research.

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advantages of Pre-trained Language Models (PLMs). It introduces two span selectors based on prompt to select start/end tokens among input texts for each role. On the other hand, we capture argument interactions via multi-role prompts, and conduct joint optimization with optimal span assignments via a bipartite matching loss. Also, with flexible prompt design, PAIE can extract multiple arguments with the same role, instead of conventional heuristic threshold tuning. We have conducted extensive experiments on three benchmarks, including both sentence- and document-level EAE. The results present a promising improvements from PAIE (1.1% and 3.8% F1 gains on average in sentence-level and document-level respectively). Further analysis demonstrates the efficiency, generalization to few-shot settings and effectiveness of different extractive prompt tuning strategies. We will release our codes upon acceptance.

SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data augmentation methods to generate positive samples, while consider other independent sentences as negative samples. Then they adopt InfoNCE loss to pull the embeddings of positive pairs gathered, and push those of negative pairs scattered. Although these models have made great progress on sentence embedding, we argue that they may suffer from feature suppression. The models fail to distinguish and decouple textual similarity and semantic similarity. And they may overestimate the semantic similarity of any pairs with similar textual regardless of the actual semantic difference between them. This is because positive pairs in unsupervised contrastive learning come with similar and even the same textual through data augmentation. To alleviate feature suppression, we propose contrastive learning for unsupervised sentence embedding with soft negative samples (SNCSE). Soft negative samples share highly similar textual but have surely and apparently different semantic with the original samples. Specifically, we take the negation of original sentences as soft negative samples, and propose Bidirectional Margin Loss (BML) to introduce them into traditional contrastive learning framework, which merely involves positive and negative samples. Our experimental results show that SNCSE can obtain state-of-the-art performance on semantic textual similarity (STS) task with average Spearman's correlation coefficient of 78.97% on BERTbase and 79.23% on RoBERTabase. Besides, we adopt rank-based error analysis method to detect the weakness of SNCSE for future study.

RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training

Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability. However, the dominant method, contrastive learning, mainly relies on an instance discrimination pretext task, which learns a global understanding of the image. This paper incorporates local feature learning into self-supervised vision transformers via Reconstructive Pre-training (RePre). Our RePre extends contrastive frameworks by adding a branch for reconstructing raw image pixels in parallel with the existing contrastive objective. RePre is equipped with a lightweight convolution-based decoder that fuses the multi-hierarchy features from the transformer encoder. The multi-hierarchy features provide rich supervisions from low to high semantic information, which are crucial for our RePre. Our RePre brings decent improvements on various contrastive frameworks with different vision transformer architectures. Transfer performance in downstream tasks outperforms supervised pre-training and state-of-the-art (SOTA) self-supervised counterparts.

ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results

The rapid progress of photorealistic synthesis techniques has reached a critical point where the boundary between real and manipulated images starts to blur. Recently, a mega-scale deep face forgery dataset, ForgeryNet which comprised of 2.9 million images and 221,247 videos has been released. It is by far the largest publicly available in terms of data-scale, manipulations (7 image-level approaches, 8 video-level approaches), perturbations (36 independent and more mixed perturbations), and annotations (6.3 million classification labels, 2.9 million manipulated area annotations, and 221,247 temporal forgery segment labels). This paper reports methods and results in the ForgeryNet - Face Forgery Analysis Challenge 2021, which employs the ForgeryNet benchmark. The model evaluation is conducted offline on the private test set. A total of 186 participants registered for the competition, and 11 teams made valid submissions. We will analyze the top-ranked solutions and present some discussion on future work directions.

A Simple Long-Tailed Recognition Baseline via Vision-Language Model

The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to address the problem. However, they still train models with a finite set of predefined labels, limiting their supervision information and restricting their transferability to novel instances. Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition. With open-vocabulary supervisions, pretrained contrastive vision-language models learn powerful multimodal representations that are promising to handle data deficiency and unseen concepts. By calculating the semantic similarity between visual and text inputs, visual recognition is converted to a vision-language matching problem. Inspired by this, we propose BALLAD to leverage contrastive vision-language models for long-tailed recognition. We first continue pretraining the vision-language backbone through contrastive learning on a specific long-tailed target dataset. Afterward, we freeze the backbone and further employ an additional adapter layer to enhance the representations of tail classes on balanced training samples built with re-sampling strategies. Extensive experiments have been conducted on three popular long-tailed recognition benchmarks. As a result, our simple and effective approach sets the new state-of-the-art performances and outperforms competitive baselines with a large margin. Code is released at https://github.com/gaopengcuhk/BALLAD.

INTERN: A New Learning Paradigm Towards General Vision

Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However, down the road, a key challenge awaits us, that is, our capability of meeting rapidly-growing scenario-specific demands is severely limited by the cost of acquiring a commensurate amount of training data. This difficult situation is in essence due to limitations of the mainstream learning paradigm: we need to train a new model for each new scenario, based on a large quantity of well-annotated data and commonly from scratch. In tackling this fundamental problem, we move beyond and develop a new learning paradigm named INTERN. By learning with supervisory signals from multiple sources in multiple stages, the model being trained will develop strong generalizability. We evaluate our model on 26 well-known datasets that cover four categories of tasks in computer vision. In most cases, our models, adapted with only 10% of the training data in the target domain, outperform the counterparts trained with the full set of data, often by a significant margin. This is an important step towards a promising prospect where such a model with general vision capability can dramatically reduce our reliance on data, thus expediting the adoption of AI technologies. Furthermore, revolving around our new paradigm, we also introduce a new data system, a new architecture, and a new benchmark, which, together, form a general vision ecosystem to support its future development in an open and inclusive manner.

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite data-hungry and requires 400M image-text pairs for pre-training, thereby restricting its adoption. This work proposes a novel training paradigm, Data efficient CLIP (DeCLIP), to alleviate this limitation. We demonstrate that by carefully utilizing the widespread supervision among the image-text pairs, our De-CLIP can learn generic visual features more efficiently. Instead of using the single image-text contrastive supervision, we fully exploit data potential through the use of (1) self-supervision within each modality; (2) multi-view supervision across modalities; (3) nearest-neighbor supervision from other similar pairs. Benefiting from intrinsic supervision, our DeCLIP-ResNet50 can achieve 60.4% zero-shot top1 accuracy on ImageNet, which is 0.8% above the CLIP-ResNet50 while using 7.1 x fewer data. Our DeCLIP-ResNet50 outperforms its counterpart in 8 out of 11 visual datasets when transferred to downstream tasks. Moreover, Scaling up the model and computing also works well in our framework.Our code, dataset and models are released at: https://github.com/Sense-GVT/DeCLIP

Few-Shot Domain Expansion for Face Anti-Spoofing

Face anti-spoofing (FAS) is an indispensable and widely used module in face recognition systems. Although high accuracy has been achieved, a FAS system will never be perfect due to the non-stationary applied environments and the potential emergence of new types of presentation attacks in real-world applications. In practice, given a handful of labeled samples from a new deployment scenario (target domain) and abundant labeled face images in the existing source domain, the FAS system is expected to perform well in the new scenario without sacrificing the performance on the original domain. To this end, we identify and address a more practical problem: Few-Shot Domain Expansion for Face Anti-Spoofing (FSDE-FAS). This problem is challenging since with insufficient target domain training samples, the model may suffer from both overfitting to the target domain and catastrophic forgetting of the source domain. To address the problem, this paper proposes a Style transfer-based Augmentation for Semantic Alignment (SASA) framework. We propose to augment the target data by generating auxiliary samples based on photorealistic style transfer. With the assistant of the augmented data, we further propose a carefully designed mechanism to align different domains from both instance-level and distribution-level, and then stabilize the performance on the source domain with a less-forgetting constraint. Two benchmarks are proposed to simulate the FSDE-FAS scenarios, and the experimental results show that the proposed SASA method outperforms state-of-the-art methods.