Probabilistic Language-Image Pre-Training

Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and texts. This oversimplifies real-world relationships, which are inherently many-to-many, with multiple captions describing a single image and vice versa. We introduce Probabilistic Language-Image Pre-training (ProLIP), the first probabilistic VLM pre-trained on a billion-scale image-text dataset using only probabilistic objectives, achieving a strong zero-shot capability (e.g., 74.6% ImageNet zero-shot accuracy with ViT-B/16). ProLIP efficiently estimates uncertainty by an "uncertainty token" without extra parameters. We also introduce a novel inclusion loss that enforces distributional inclusion relationships between image-text pairs and between original and masked inputs. Experiments demonstrate that, by leveraging uncertainty estimates, ProLIP benefits downstream tasks and aligns with intuitive notions of uncertainty, e.g., shorter texts being more uncertain and more general inputs including specific ones. Utilizing text uncertainties, we further improve ImageNet accuracy from 74.6% to 75.8% (under a few-shot setting), supporting the practical advantages of our probabilistic approach. The code is available at https://github.com/naver-ai/prolip

Read, Watch and Scream! Sound Generation from Text and Video

Multimodal generative models have shown impressive advances with the help of powerful diffusion models. Despite the progress, generating sound solely from text poses challenges in ensuring comprehensive scene depiction and temporal alignment. Meanwhile, video-to-sound generation limits the flexibility to prioritize sound synthesis for specific objects within the scene. To tackle these challenges, we propose a novel video-and-text-to-sound generation method, called ReWaS, where video serves as a conditional control for a text-to-audio generation model. Our method estimates the structural information of audio (namely, energy) from the video while receiving key content cues from a user prompt. We employ a well-performing text-to-sound model to consolidate the video control, which is much more efficient for training multimodal diffusion models with massive triplet-paired (audio-video-text) data. In addition, by separating the generative components of audio, it becomes a more flexible system that allows users to freely adjust the energy, surrounding environment, and primary sound source according to their preferences. Experimental results demonstrate that our method shows superiority in terms of quality, controllability, and training efficiency. Our demo is available at https://naver-ai.github.io/rewas

Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable searches. Due to the expensive dataset construction cost for CIR triplets, a zero-shot (ZS) CIR setting has been actively studied to eliminate the need for human-collected triplet datasets. The mainstream of ZS-CIR employs an efficient projection module that projects a CLIP image embedding to the CLIP text token embedding space, while fixing the CLIP encoders. Using the projected image embedding, these methods generate image-text composed features by using the pre-trained text encoder. However, their CLIP image and text encoders suffer from the task discrepancy between the pre-training task (text $\leftrightarrow$ image) and the target CIR task (image + text $\leftrightarrow$ image). Conceptually, we need expensive triplet samples to reduce the discrepancy, but we use cheap text triplets instead and update the text encoder. To that end, we introduce the Reducing Task Discrepancy of text encoders for Composed Image Retrieval (RTD), a plug-and-play training scheme for the text encoder that enhances its capability using a novel target-anchored text contrastive learning. We also propose two additional techniques to improve the proposed learning scheme: a hard negatives-based refined batch sampling strategy and a sophisticated concatenation scheme. Integrating RTD into the state-of-the-art projection-based ZS-CIR methods significantly improves performance across various datasets and backbones, demonstrating its efficiency and generalizability.

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts

In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addressing this, we introduce HYPerbolic Entailment filtering (HYPE), a novel methodology designed to meticulously extract modality-wise meaningful and well-aligned data from extensive, noisy image-text pair datasets. Our approach leverages hyperbolic embeddings and the concept of entailment cones to evaluate and filter out samples with meaningless or underspecified semantics, focusing on enhancing the specificity of each data sample. HYPE not only demonstrates a significant improvement in filtering efficiency but also sets a new state-of-the-art in the DataComp benchmark when combined with existing filtering techniques. This breakthrough showcases the potential of HYPE to refine the data selection process, thereby contributing to the development of more accurate and efficient self-supervised learning models. Additionally, the image specificity $\epsilon_{i}$ can be independently applied to induce an image-only dataset from an image-text or image-only data pool for training image-only self-supervised models and showed superior performance when compared to the dataset induced by CLIP score.

Toward Interactive Regional Understanding in Vision-Large Language Models

Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements. Nevertheless, these models heavily rely on image-text pairs that capture only coarse and global information of an image, leading to a limitation in their regional understanding ability. In this work, we introduce \textbf{RegionVLM}, equipped with explicit regional modeling capabilities, allowing them to understand user-indicated image regions. To achieve this, we design a simple yet innovative architecture, requiring no modifications to the model architecture or objective function. Additionally, we leverage a dataset that contains a novel source of information, namely Localized Narratives, which has been overlooked in previous VLP research. Our experiments demonstrate that our single generalist model not only achieves an interactive dialogue system but also exhibits superior performance on various zero-shot region understanding tasks, without compromising its ability for global image understanding.

Language-only Efficient Training of Zero-shot Composed Image Retrieval

Composed image retrieval (CIR) task takes a composed query of image and text, aiming to search relative images for both conditions. Conventional CIR approaches need a training dataset composed of triplets of query image, query text, and target image, which is very expensive to collect. Several recent works have worked on the zero-shot (ZS) CIR paradigm to tackle the issue without using pre-collected triplets. However, the existing ZS-CIR methods show limited backbone scalability and generalizability due to the lack of diversity of the input texts during training. We propose a novel CIR framework, only using language for its training. Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP). We project the text latent embedding to the token embedding space and construct a new text by replacing the keyword tokens of the original text. Then, we let the new and original texts have the same latent embedding vector. With this simple strategy, LinCIR is surprisingly efficient and highly effective; LinCIR with CLIP ViT-G backbone is trained in 48 minutes and shows the best ZS-CIR performances on four different CIR benchmarks, CIRCO, GeneCIS, FashionIQ, and CIRR, even outperforming supervised method on FashionIQ. Code is available at https://github.com/navervision/lincir

Longer-range Contextualized Masked Autoencoder

Masked image modeling (MIM) has emerged as a promising self-supervised learning (SSL) strategy. The MIM pre-training facilitates learning powerful representations using an encoder-decoder framework by randomly masking some input pixels and reconstructing the masked pixels from the remaining ones. However, as the encoder is trained with partial pixels, the MIM pre-training can suffer from a low capability of understanding long-range dependency. This limitation may hinder its capability to fully understand multiple-range dependencies, resulting in narrow highlighted regions in the attention map that may incur accuracy drops. To mitigate the limitation, We propose a self-supervised learning framework, named Longer-range Contextualized Masked Autoencoder (LC-MAE). LC-MAE effectively leverages a global context understanding of visual representations while simultaneously reducing the spatial redundancy of input at the same time. Our method steers the encoder to learn from entire pixels in multiple views while also learning local representation from sparse pixels. As a result, LC-MAE learns more discriminative representations, leading to a performance improvement of achieving 84.2% top-1 accuracy with ViT-B on ImageNet-1K with 0.6%p gain. We attribute the success to the enhanced pre-training method, as evidenced by the singular value spectrum and attention analyses. Finally, LC-MAE achieves significant performance gains at the downstream semantic segmentation and fine-grained visual classification tasks; and on diverse robust evaluation metrics. Our code will be publicly available.

Improved Probabilistic Image-Text Representations

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further; first, the incorporation of pseudo-positives to prevent the loss saturation problem under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt tuning for zero-shot classification is shown. The code is available at https://naver-ai.github.io/pcmepp/.

RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models

Recently, large-scale vision-language pre-training models and visual semantic embedding methods have significantly improved image-text matching (ITM) accuracy on MS COCO 5K test set. However, it is unclear how robust these state-of-the-art (SOTA) models are when using them in the wild. In this paper, we propose a novel evaluation benchmark to stress-test the robustness of ITM models. To this end, we add various fooling images and captions to a retrieval pool. Specifically, we change images by inserting unrelated images, and change captions by substituting a noun, which can change the meaning of a sentence. We discover that just adding these newly created images and captions to the test set can degrade performances (i.e., Recall@1) of a wide range of SOTA models (e.g., 81.9% $\rightarrow$ 64.5% in BLIP, 66.1% $\rightarrow$ 37.5% in VSE$\infty$). We expect that our findings can provide insights for improving the robustness of the vision-language models and devising more diverse stress-test methods in cross-modal retrieval task. Source code and dataset will be available at https://github.com/pseulki/rococo.

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs). Recently, 3D pseudo-GTs have been widely used to train 3D human mesh estimation networks as the 3D pseudo-GTs enable 3D mesh supervision when training the networks on ITW datasets. However, despite the great potential of the 3D pseudo-GTs, there has been no extensive analysis that investigates which factors are important to make more beneficial 3D pseudo-GTs. In this paper, we provide three recipes to obtain highly beneficial 3D pseudo-GTs of ITW datasets. The main challenge is that only 2D-based weak supervision is allowed when obtaining the 3D pseudo-GTs. Each of our three recipes addresses the challenge in each aspect: depth ambiguity, sub-optimality of weak supervision, and implausible articulation. Experimental results show that simply re-training state-of-the-art networks with our new 3D pseudo-GTs elevates their performance to the next level without bells and whistles. The 3D pseudo-GT is publicly available in https://github.com/mks0601/NeuralAnnot_RELEASE.