Visual Question Answering (VQA)

GPT-4 is a transformer based model pre-trained to predict the next token in a document.

Conditional Batch Normalization (CBN) is a class-conditional variant of batch normalization. The key idea is to predict the $\gamma$ and $\beta$ of the batch normalization from an embedding - e.g. a language embedding in VQA. CBN enables the linguistic embedding to manipulate entire feature maps by scaling them up or down, negating them, or shutting them off. CBN has also been used in GANs to allow class information to affect the batch normalization parameters. Consider a single convolutional layer with batch normalization module $\text{BN}\left(F\_{i,c,h,w}|\gamma\_{c}, \beta\_{c}\right)$ for which pretrained scalars $\gamma\_{c}$ and $\beta\_{c}$ are available. We would like to directly predict these affine scaling parameters from, e.g., a language embedding $\mathbf{e\_{q}}$. When starting the training procedure, these parameters must be close to the pretrained values to recover the original ResNet model as a poor initialization could significantly deteriorate performance. Unfortunately, it is difficult to initialize a network to output the pretrained $\gamma$ and $\beta$. For these reasons, the authors propose to predict a change $\delta\beta\_{c}$ and $\delta\gamma\_{c}$ on the frozen original scalars, for which it is straightforward to initialize a neural network to produce an output with zero-mean and small variance. The authors use a one-hidden-layer MLP to predict these deltas from a question embedding $\mathbf{e\_{q}}$ for all feature maps within the layer: $$\Delta\beta = \text{MLP}\left(\mathbf{e\_{q}}\right)$$ $$\Delta\gamma = \text{MLP}\left(\mathbf{e\_{q}}\right)$$ So, given a feature map with $C$ channels, these MLPs output a vector of size $C$. We then add these predictions to the $\beta$ and $\gamma$ parameters: $$ \hat{\beta}\_{c} = \beta\_{c} + \Delta\beta\_{c} $$ $$ \hat{\gamma}\_{c} = \gamma\_{c} + \Delta\gamma\_{c} $$ Finally, these updated $\hat{β}$ and $\hat{\gamma}$ are used as parameters for the batch normalization: $\text{BN}\left(F\_{i,c,h,w}|\hat{\gamma\_{c}}, \hat{\beta\_{c}}\right)$. The authors freeze all ResNet parameters, including $\gamma$ and $\beta$, during training. A ResNet consists of four stages of computation, each subdivided in several residual blocks. In each block, the authors apply CBN to the three convolutional layers.

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to video-language tasks in a zero-shot manner. Code, models, and datasets are released at https://github.com/salesforce/BLIP.

Conditional Relation Network, or CRN, is a building block to construct more sophisticated structures for representation and reasoning over video. CRN takes as input an array of tensorial objects and a conditioning feature, and computes an array of encoded output objects. Model building becomes a simple exercise of replication, rearrangement and stacking of these reusable units for diverse modalities and contextual information. This design thus supports high-order relational and multi-step reasoning.

LXMERT is a model for learning vision-and-language cross-modality representations. It consists of a Transformer model that consists three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. The model takes two inputs: image with its related sentence. The images are represented as a sequence of objects, whereas each sentence is represented as sequence of words. By combining the self-attention and cross-attention layers the model is able to generated language representation, image representations, and cross-modality representations from the input. The model is pre-trained with image-sentence pairs via five pre-training tasks: masked language modeling, masked object prediction, cross-modality matching, and image questions answering. These tasks help the model to learn both intra-modality and cross-modality relationships.

OSCAR is a new learning method that uses object tags detected in images as anchor points to ease the learning of image-text alignment. The model take a triple as input (word-tag-region) and pre-trained with two losses (masked token loss over words and tags, and a contrastive loss between tags and others). OSCAR represents an image-text pair into semantic space via dictionary lookup. Object tags are used as anchor points to align image regions with word embeddings of pre-trained language models. The model is then fine-tuned for understanding and generation tasks.

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https://github.com/OFA-Sys/OFA.

Vision-and-Language BERT (ViLBERT) is a BERT-based model for learning task-agnostic joint representations of image content and natural language. ViLBERT extend the popular BERT architecture to a multi-modal two-stream model, processing both visual and textual inputs in separate streams that interact through co-attentional transformer layers.

VisualBERT aims to reuse self-attention to implicitly align elements of the input text and regions in the input image. Visual embeddings are used to model images where the representations are represented by a bounding region in an image obtained from an object detector. These visual embeddings are constructed by summing three embeddings: 1) visual feature representation, 2) a segment embedding indicate whether it is an image embedding, and 3) position embedding. Essentially, image regions and language are combined with a Transformer to allow self-attention to discover implicit alignments between language and vision. VisualBERT is trained using COCO, which consists of images paired with captions. It is pre-trained using two objectives: masked language modeling objective and sentence-image prediction task. It can then be fine-tuned on different downstream tasks.

UNITER or UNiversal Image-TExt Representation model is a large-scale pre-trained model for joint multimodal embedding. It is pre-trained using four image-text datasets COCO, Visual Genome, Conceptual Captions, and SBU Captions. It can power heterogeneous downstream V+L tasks with joint multimodal embeddings. UNITER takes the visual regions of the image and textual tokens of the sentence as inputs. A faster R-CNN is used in Image Embedder to extract the visual features of each region and a Text Embedder is used to tokenize the input sentence into WordPieces. It proposes WRA via the Optimal Transport to provide more fine-grained alignment between word tokens and image regions that is effective in calculating the minimum cost of transporting the contextualized image embeddings to word embeddings and vice versa. Four pretraining tasks were designed for this model. They are Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image-Text Matching (ITM), and Word-Region Alignment (WRA). This model is different from the previous models because it uses conditional masking on pre-training tasks.

ALBEF introduces a contrastive loss to align the image and text representations before fusing them through cross-modal attention. This enables more grounded vision and language representation learning. ALBEF also doesn't require bounding box annotations. The model consists of an image encode, a text encoder, and a multimodal encoder. The image-text contrastive loss helps to align the unimodal representations of an image-text pair before fusion. The image-text matching loss and a masked language modeling loss are applied to learn multimodal interactions between image and text. In addition, momentum distillation is used to generate pseudo-targets. This improves learning with noisy data.

MDETR is an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. It utilizes a transformer-based architecture to reason jointly over text and image by fusing the two modalities at an early stage of the model. The network is pre-trained on 1.3M text-image pairs, mined from pre-existing multi-modal datasets having explicit alignment between phrases in text and objects in the image. The network is then fine-tuned on several downstream tasks such as phrase grounding, referring expression comprehension and segmentation.

Florence is a computer vision foundation model aiming to learn universal visual-language representations that be adapted to various computer vision tasks, visual question answering, image captioning, video retrieval, among other tasks. Florence's workflow consists of data curation, unified learning, Transformer architectures and adaption. Florence is pre-trained in an image-label-description space, utilizing a unified image-text contrastive learning. It involves a two-tower architecture: 12-layer Transformer for the language encoder, and a Vision Transformer for the image encoder. Two linear projection layers are added on top of the image encoder and language encoder to match the dimensions of image and language features. Compared to previous methods for cross-modal shared representations, Florence expands beyond simple classification and retrieval capabilities to advanced representations that support object level, multiple modality, and videos respectively.

A general multimodal attention unit for any number of modalities. Graphical models inspire it, i.e., it infers several attention beliefs via aggregated interaction messages.

ViLT is a minimal vision-and-language pre-training transformer model where processing of visual inputs is simplified to just the same convolution-free manner that text inputs are processed. The model-specific components of ViLT require less computation than the transformer component for multimodal interactions. ViLTThe model is pre-trained on the following objectives: image text matching, masked language modeling, and word patch alignment.

VL-T5 is a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation. The model learns to generate labels in text based on the visual and textual inputs. In contrast to other existing methods, the framework unifies tasks as generating text labels conditioned on multimodal inputs. This allows the model to tackle vision-and-language tasks with unified text generation objective. The models use text prefixes to adapt to different tasks.

VL-BERT is pre-trained on a large-scale image-captions dataset together with text-only corpus. The input to the model are either words from the input sentences or regions-of-interest (RoI) from input images. It can be fine-tuned to fit most visual-linguistic downstream tasks. Its backbone is a multi-layer bidirectional Transformer encoder, modified to accommodate visual contents, and new type of visual feature embedding to the input feature embeddings. VL-BERT takes both visual and linguistic elements as input, represented as RoIs in images and subwords in input sentences. Four different types of embeddings are used to represent each input: token embedding, visual feature embedding, segment embedding, and sequence position embedding. VL-BERT is pre-trained using Conceptual Captions and text-only datasets. Two pre-training tasks are used: masked language modeling with visual clues, and masked RoI classification with linguistic clues.

CLIPort, a language-conditioned imitation-learning agent that combines the broad semantic understanding (what) of CLIP [1] with the spatial precision (where) of Transporter [2].

SimVLM is a minimalist pretraining framework to reduce training complexity by exploiting large-scale weak supervision. It is trained end-to-end with a single prefix language modeling (PrefixLM) objective. PrefixLM enables bidirectional attention within the prefix sequence, and thus it is applicable for both decoder-only and encoder-decoder sequence-to-sequence language models.

Pixel-BERT is a pre-trained model trained to align image pixels with text. The end-to-end framework includes a CNN-based visual encoder and cross-modal transformers for visual and language embedding learning. This model has three parts: one fully convolutional neural network that takes pixels of an image as input, one word-level token embedding based on BERT, and a multimodal transformer for jointly learning visual and language embedding. For language, it uses other pretraining works to use Masked Language Modeling (MLM) to predict masked tokens with surrounding text and images. For vision, it uses the random pixel sampling mechanism that makes up for the challenge of predicting pixel-level features. This mechanism is also suitable for solving overfitting issues and improving the robustness of visual features. It applies Image-Text Matching (ITM) to classify whether an image and a sentence pair match for vision and language interaction. Image captioning is required to understand language and visual semantics for cross-modality tasks like VQA. Region-based visual features extracted from object detection models like Faster RCNN are used for better performance in the newer version of the model.

Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework, resulting in impressive results. CLIP imposes a bidirectional constraints on global representation of entire images and sentences. Although IC conducts an unidirectional image-to-text generation on local representation, it lacks any constraint on local text-to-image reconstruction, which limits the ability to understand images at a fine-grained level when aligned with texts. To achieve multimodal alignment from both global and local perspectives, this paper proposes Symmetrizing Contrastive Captioners (SyCoCa), which introduces bidirectional interactions on images and texts across the global and local representation levels. Specifically, we expand a Text-Guided Masked Image Modeling (TG-MIM) head based on ITC and IC heads. The improved SyCoCa can further leverage textual cues to reconstruct contextual images and visual cues to predict textual contents. When implementing bidirectional local interactions, the local contents of images tend to be cluttered or unrelated to their textual descriptions. Thus, we employ an attentive masking strategy to select effective image patches for interaction. Extensive experiments on five vision-language tasks, including image-text retrieval, image-captioning, visual question answering, and zero-shot/finetuned image classification, validate the effectiveness of our proposed method.

ClipBERT is a framework for end-to-end-learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. Two aspects distinguish ClipBERT from previous work. First, in contrast to densely extracting video features (adopted by most existing methods), CLIPBERT sparsely samples only one single or a few short clips from the full-length videos at each training step. The hypothesis is that visual features from sparse clips already capture key visual and semantic information in the video, as consecutive clips usually contain similar semantics from a continuous scene. Thus, a handful of clips are sufficient for training, instead of using the full video. Then, predictions from multiple densely-sampled clips are aggregated to obtain the final video-level prediction during inference, which is less computational demanding. The second differentiating aspect concerns the initialization of model weights (i.e., transfer through pre-training). The authors use 2D architectures (e.g., ResNet-50) instead of 3D features as the visual backbone for video encoding, allowing them to harness the power of image-text pretraining for video-text understanding along with the advantages of low memory cost and runtime efficiency.

A VQA model that marries two powerful ideas: probabilistic neural symbolic program execution for reasoning and a deep neural network with 3D generative representations of objects for robust visual scene parsing.

VC R-CNN is an unsupervised feature representation learning method, which uses Region-based Convolutional Neural Network (R-CNN) as the visual backbone, and the causal intervention as the training objective. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as the chair is likely to exist if table is observed.

VLMo is a unified vision-language pre-trained model that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. A Mixture-of-Modality-Experts (MOME) transformer is introduced to encode different modalities which helps it to capture modality-specific information by modality experts, and align content of different modalities by the self-attention module shared across modalities. The model parameters are shared across image-text contrastive learning, masked language modeling, and image-text matching tasks. During fine-tuning, the flexible modeling allows for VLMO to be used as either a dual encoder (i.e., separately encode images and text for retrieval tasks) or a fusion encoder (i.e., jointly encode image-text pairs for better interaction across modalities) Stage-wise pretraining on image-only and text-only data improved the vision-language pre-trained model. The model can be used for classification tasks and fine-tuned as a dual encoder for retrieval tasks.

Visual-Spatial-Graph Network (VSGNet) is a network for human-object interaction detection. It extracts visual features from the image representing the human-object pair, refines the features with spatial configurations of the pair, and utilizes the structural connections between the pair via graph convolutions.

XGPT is a method of cross-modal generative pre-training for image captioning designed to pre-train text-to-image caption generators through three novel generation tasks, including image-conditioned masked language modeling (IMLM), image-conditioned denoising autoencoding (IDA), and text-conditioned image feature generation (TIGF). The pre-trained XGPT can be fine-tuned without any task-specific architecture modifications and build strong image captioning models.