The objectives of this work are cross-modal text-audio and audio-text retrieval, in which the goal is to retrieve the audio content from a pool of candidates that best matches a given written description and vice versa. Text-audio retrieval enables users to search large databases through an intuitive interface: they simply issue free-form natural language descriptions of the sound they would like to hear. To study the tasks of text-audio and audio-text retrieval, which have received limited attention in the existing literature, we introduce three challenging new benchmarks. We first construct text-audio and audio-text retrieval benchmarks from the AudioCaps and Clotho audio captioning datasets. Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho. We employ these three benchmarks to establish baselines for cross-modal text-audio and audio-text retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into audio retrieval with free-form text queries. Code, audio features for all datasets used, and the SoundDescs dataset are publicly available at https://github.com/akoepke/audio-retrieval-benchmark.
We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimization of its contrastive learning objective. We accomplish this by taking advantage of an information efficient lower-bound to maximize the mutual information between the two input modalities. This allows CLIP-Lite to be trained with significantly reduced amounts of data and batch sizes while obtaining better performance than CLIP at the same scale. We evaluate CLIP-Lite by pretraining on the COCO-Captions dataset and testing transfer learning to other datasets. CLIP-Lite obtains a +14.0% mAP absolute gain in performance on Pascal VOC classification, and a +22.1% top-1 accuracy gain on ImageNet, while being comparable or superior to other, more complex, text-supervised models. CLIP-Lite is also superior to CLIP on image and text retrieval, zero-shot classification, and visual grounding. Finally, we show that CLIP-Lite can leverage language semantics to encourage bias-free visual representations that can be used in downstream tasks. Implementation: https://github.com/4m4n5/CLIP-Lite
Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream tasks, e.g., visual question answering, image-text retrieval and visual entailment, they do not possess the ability to generate. To tackle this problem, we propose Unified multimodal pre-training for both Vision-Language understanding and generation (UniVL). The proposed UniVL is capable of handling both understanding tasks and generative tasks. We augment existing pretraining paradigms that only use random masks with causal masks, i.e., triangular masks that mask out future tokens, such that the pre-trained models can have autoregressive generation abilities by design. We formulate several previous understanding tasks as a text generation task and propose to use prompt-based method for fine-tuning on different downstream tasks. Our experiments show that there is a trade-off between understanding tasks and generation tasks while using the same model, and a feasible way to improve both tasks is to use more data. Our UniVL framework attains comparable performance to recent vision-language pre-training methods on both understanding tasks and generation tasks. Moreover, we demostrate that prompt-based finetuning is more data-efficient - it outperforms discriminative methods in few-shot scenarios.
Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust. Prior work combines dense and sparse retrievers by fusing their model scores. As an alternative, this paper presents a simple approach to densifying sparse representations for text retrieval that does not involve any training. Our densified sparse representations (DSRs) are interpretable and can be easily combined with dense representations for end-to-end retrieval. We demonstrate that our approach can jointly learn sparse and dense representations within a single model and then combine them for dense retrieval. Experimental results suggest that combining our DSRs and dense representations yields a balanced tradeoff between effectiveness and efficiency.
Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account the structure of objects during pre-training on large-scale video-text pairs. Given a video, our module (1) first quantizes visual features into semantic clusters, then (2) generates learnable masks and uses them to aggregate the features belonging to the same semantic region, and finally (3) models the interactions between different aggregated regions. In contrast to using off-the-shelf object detectors, our proposed module does not require explicit supervision and is much more computationally efficient. We pre-train the proposed approach on the public WebVid2M and CC3M datasets. Extensive evaluations on four downstream video-text retrieval benchmarks clearly demonstrate the effectiveness of our RegionLearner. The code will be available at https://github.com/ruiyan1995/Region_Learner.
In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question), for vision-language (VL) representation learning. Existing approaches typically design an individual network for each modality and/or a specific fusion network for multimodal tasks. To simplify the network architecture, we use a single transformer network and enforce multi-task learning during VL pre-training, which includes the image-text contrastive loss, image-text matching loss, and masked language modeling loss based on the bidirectional and the seq2seq attention mask. The same transformer network is used as the image encoder, the text encoder, or the fusion network in different pre-training tasks. Empirically, we observe less conflict among different tasks and achieve new state of the arts on visual question answering, COCO image captioning (cross-entropy optimization) and nocaps (in SPICE). On other downstream tasks, e.g., image-text retrieval, we also achieve competitive performance.
Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which misses sufficient information, or finer-grained interactions using cross/self-attention upon visual and textual tokens. However, cross/self-attention suffers from inferior efficiency in both training and inference. In this paper, we introduce a large-scale Fine-grained Interactive Language-Image Pre-training (FILIP) to achieve finer-level alignment through a cross-modal late interaction mechanism, which uses a token-wise maximum similarity between visual and textual tokens to guide the contrastive objective. FILIP successfully leverages the finer-grained expressiveness between image patches and textual words by modifying only contrastive loss, while simultaneously gaining the ability to pre-compute image and text representations offline at inference, keeping both large-scale training and inference efficient. Furthermore, we construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks including zero-shot image classification and image-text retrieval. The visualization on word-patch alignment further shows that FILIP can learn meaningful fine-grained features with promising localization ability.
We tackle the cross-modal retrieval problem, where learning is only supervised by relevant multi-modal pairs in the data. Although the contrastive learning is the most popular approach for this task, it makes potentially wrong assumption that the instances in different pairs are automatically irrelevant. To address the issue, we propose a novel loss function that is based on self-labeling of the unknown semantic classes. Specifically, we aim to predict class labels of the data instances in each modality, and assign those labels to the corresponding instances in the other modality (i.e., swapping the pseudo labels). With these swapped labels, we learn the data embedding for each modality using the supervised cross-entropy loss. This way, cross-modal instances from different pairs that are semantically related can be aligned to each other by the class predictor. We tested our approach on several real-world cross-modal retrieval problems, including text-based video retrieval, sketch-based image retrieval, and image-text retrieval. For all these tasks our method achieves significant performance improvement over the contrastive learning.
Modern video-text retrieval frameworks basically consist of three parts: video encoder, text encoder and the similarity head. With the success on both visual and textual representation learning, transformer based encoders and fusion methods have also been adopted in the field of video-text retrieval. In this report, we present CLIP2TV, aiming at exploring where the critical elements lie in transformer based methods. To achieve this, We first revisit some recent works on multi-modal learning, then introduce some techniques into video-text retrieval, finally evaluate them through extensive experiments in different configurations. Notably, CLIP2TV achieves 52.9@R1 on MSR-VTT dataset, outperforming the previous SOTA result by 4.1%.
Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current retrieval-based negative sample construction approach is limited in the scale of the dataset thus fail to identify negative sample of high difficulty for every image. We propose our TAiloring neGative Sentences with Discrimination and Correction (TAGS-DC) to generate synthetic sentences automatically as negative samples. TAGS-DC is composed of masking and refilling to generate synthetic negative sentences with higher difficulty. To keep the difficulty during training, we mutually improve the retrieval and generation through parameter sharing. To further utilize fine-grained semantic of mismatch in the negative sentence, we propose two auxiliary tasks, namely word discrimination and word correction to improve the training. In experiments, we verify the effectiveness of our model on MS-COCO and Flickr30K compared with current state-of-the-art models and demonstrates its robustness and faithfulness in the further analysis. Our code is available in https://github.com/LibertFan/TAGS.
Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. Though previous studies have made substantial efforts for automated keyphrase extraction and generation, surprisingly, few studies have been made for \textit{keyphrase completion} (KPC). KPC aims to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases, which can be applied to improve text indexing system, etc. In this paper, we propose a novel KPC method with an encoder-decoder framework. We name it \textit{deep keyphrase completion} (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework. Specifically, the encoder and the decoder in DKPC play different roles to make full use of the known keyphrases. The former considers the keyphrase-guiding factors, which aggregates information of known keyphrases into context. On the contrary, the latter considers the keyphrase-inhibited factor to inhibit semantically repeated keyphrase generation. Extensive experiments on benchmark datasets demonstrate the efficacy of our proposed model.
We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA, NLVR2 and image-text retrieval. The code and pretrained models are available at https://aka.ms/vlmo.
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense retrievers require splitting documents into short passages that usually contain local, partial, and sometimes biased context, and highly depend on the splitting process. As a consequence, it may yield inaccurate and misleading hidden representations, thus deteriorating the final retrieval result. In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework that can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage. Specifically, a document-level retriever first identifies relevant documents, among which relevant passages are then retrieved by a passage-level retriever. The ranking of the retrieved passages will be further calibrated by examining the document-level relevance. In addition, hierarchical title structure and two negative sampling strategies (i.e., In-Doc and In-Sec negatives) are investigated. We apply DHR to large-scale open-domain QA datasets. DHR significantly outperforms the original dense passage retriever and helps an end-to-end QA system outperform the strong baselines on multiple open-domain QA benchmarks.
Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding space and then matching them by nearest neighbor search. This requires strong locality properties from the representation space, i.e, the close allocations of each small group of relevant texts, which are hard to generalize to domains without sufficient training data. In this paper, we aim to improve the generalization ability of DR models from source training domains with rich supervision signals to target domains without any relevant labels, in the zero-shot setting. To achieve that, we propose Momentum adversarial Domain Invariant Representation learning (MoDIR), which introduces a momentum method in the DR training process to train a domain classifier distinguishing source versus target, and then adversarially updates the DR encoder to learn domain invariant representations. Our experiments show that MoDIR robustly outperforms its baselines on 10+ ranking datasets from the BEIR benchmark in the zero-shot setup, with more than 10% relative gains on datasets with enough sensitivity for DR models' evaluation. Source code of this paper will be released.
Video-text retrieval has many real-world applications such as media analytics, surveillance, and robotics. This paper presents the 1st place solution to the video retrieval track of the ICCV VALUE Challenge 2021. We present a simple yet effective approach to jointly tackle two video-text retrieval tasks (video retrieval and video corpus moment retrieval) by leveraging the model trained only on the video retrieval task. In addition, we create an ensemble model that achieves the new state-of-the-art performance on all four datasets (TVr, How2r, YouCook2r, and VATEXr) presented in the VALUE Challenge.
Current dense text retrieval models face two typical challenges. First, they adopt a siamese dual-encoder architecture to encode queries and documents independently for fast indexing and searching, while neglecting the finer-grained term-wise interactions. This results in a sub-optimal recall performance. Second, their model training highly relies on a negative sampling technique to build up the negative documents in their contrastive losses. To address these challenges, we present Adversarial Retriever-Ranker (AR2), which consists of a dual-encoder retriever plus a cross-encoder ranker. The two models are jointly optimized according to a minimax adversarial objective: the retriever learns to retrieve negative documents to cheat the ranker, while the ranker learns to rank a collection of candidates including both the ground-truth and the retrieved ones, as well as providing progressive direct feedback to the dual-encoder retriever. Through this adversarial game, the retriever gradually produces harder negative documents to train a better ranker, whereas the cross-encoder ranker provides progressive feedback to improve retriever. We evaluate AR2 on three benchmarks. Experimental results show that AR2 consistently and significantly outperforms existing dense retriever methods and achieves new state-of-the-art results on all of them. This includes the improvements on Natural Questions R@5 to 77.9%(+2.1%), TriviaQA R@5 to 78.2%(+1.4), and MS-MARCO MRR@10 to 39.5%(+1.3%). Code and models are available at https://github.com/microsoft/AR2.
This paper outlines a conceptual framework for understanding recent developments in information retrieval and natural language processing that attempts to integrate dense and sparse retrieval methods. I propose a representational approach that breaks the core text retrieval problem into a logical scoring model and a physical retrieval model. The scoring model is defined in terms of encoders, which map queries and documents into a representational space, and a comparison function that computes query-document scores. The physical retrieval model defines how a system produces the top-$k$ scoring documents from an arbitrarily large corpus with respect to a query. The scoring model can be further analyzed along two dimensions: dense vs. sparse representations and supervised (learned) vs. unsupervised approaches. I show that many recently proposed retrieval methods, including multi-stage ranking designs, can be seen as different parameterizations in this framework, and that a unified view suggests a number of open research questions, providing a roadmap for future work. As a bonus, this conceptual framework establishes connections to sentence similarity tasks in natural language processing and information access "technologies" prior to the dawn of computing.
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of their input embeddings and exclude them from the negative samples to avoid issues with false negatives. We show that these principles consistently improve the quality of the learned embeddings. The joint embeddings learned with CrossCLR extend the state of the art in video-text retrieval on Youcook2 and LSMDC datasets and in video captioning on Youcook2 dataset by a large margin. We also demonstrate the generality of the concept by learning improved joint embeddings for other pairs of modalities.
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extract entities and triples as the phrase-level labels. In order to integrate both supervision of sentence-level and phrase-level, we propose Semantic Structure Aware Multimodal Transformer (SSAMT) for multi-modal representation learning. Inside the SSAMT, we utilize different kinds of attention mechanisms to enforce interactions of multi-grain semantic units in both sides of vision and language. For the training, we propose multi-scale matching losses from both global and local perspectives, and penalize mismatched phrases. Experimental results on MS-COCO and Flickr30K show the effectiveness of our approach compared to some state-of-the-art models.
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.